Paper Digest: AAAI 2021 Highlights
Readers can also choose to read this highlight article on our console, which allows users to filter out papers using keywords. The AAAI Conference on Artificial Intelligence (AAAI) is one of the top artificial intelligence conferences in the world. In 2021, it is to be held online.
To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights / summaries to quickly get the main idea of each paper. For users searching for papers/patents/grants with highlights, related papers, patents, grants, experts and organizations, please try our search console. We also provide an exclusive professor search service to find more than 400K professors across the US using their research work.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: AAAI 2021 Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. |
Longyuan Li; Jihai Zhang; Junchi Yan; Yaohui Jin; Yunhao Zhang; Yanjie Duan; Guangjian Tian; |
| 2 | Bayesian Distributional Policy Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous works in distributional RL focused mainly on computing the state-action-return distributions, here we model the state-return distributions. |
Luchen Li; A. Aldo Faisal; |
| 3 | Learning Graph Neural Networks with Approximate Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. |
Qunwei Li; Shaofeng Zou; Wenliang Zhong; |
| 4 | Multi-View Representation Learning with Manifold Smoothness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the manifold smoothness into multi-view representation learning and propose MvDGAT which learns the representation and the intrinsic manifold simultaneously with graph attention network. |
Shu Li; Wei Wang; Wen-Tao Li; Pan Chen; |
| 5 | Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple yet effective method, namely Bi-Classifier Determinacy Maximization (BCDM), to tackle this problem. |
Shuang Li; Fangrui Lv; Binhui Xie; Chi Harold Liu; Jian Liang; Chen Qin; |
| 6 | Sublinear Classical and Quantum Algorithms for General Matrix Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate sublinear classical and quantum algorithms for matrix games, a fundamental problem in optimization and machine learning, with provable guarantees. |
Tongyang Li; Chunhao Wang; Shouvanik Chakrabarti; Xiaodi Wu; |
| 7 | A Free Lunch for Unsupervised Domain Adaptive Object Detection Without Source Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, self-entropy descent (SED) is a metric proposed to search an appropriate confidence threshold for reliable pseudo label generation without using any handcrafted labels. |
Xianfeng Li; Weijie Chen; Di Xie; Shicai Yang; Peng Yuan; Shiliang Pu; Yueting Zhuang; |
| 8 | Improving Adversarial Robustness Via Probabilistically Compact Loss with Logit Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Many methods have been proposed to improve adversarial robustness (e.g., adversarial training and new loss functions to learn adversarially robust feature representations). |
Xin Li; Xiangrui Li; Deng Pan; Dongxiao Zhu; |
| 9 | MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present MFES-HB, an efficient Hyperband method that is capable of utilizing both the high-fidelity and low-fidelity measurements to accelerate the convergence of HPO tasks. |
Yang Li; Yu Shen; Jiawei Jiang; Jinyang Gao; Ce Zhang; Bin Cui; |
| 10 | Learned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. |
Yangyang Li; Lin Kong; Fanhua Shang; Yuanyuan Liu; Hongying Liu; Zhouchen Lin; |
| 11 | One-shot Graph Neural Architecture Search with Dynamic Search Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel dynamic one-shot search space for multi-branch neural architectures of GNNs. |
Yanxi Li; Zean Wen; Yunhe Wang; Chang Xu; |
| 12 | Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we start with a two-stream decoupled design of encoder-decoder structure, in which two decoupled cross-modal encoder and decoder are involved to separately perform each type of proxy tasks, for simultaneous VL understanding and generation pretraining. |
Yehao Li; Yingwei Pan; Ting Yao; Jingwen Chen; Tao Mei; |
| 13 | Online Optimal Control with Affine Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, we propose Online Gradient Descent with Buffer Zones (OGD-BZ). |
Yingying Li; Subhro Das; Na Li; |
| 14 | TRQ: Ternary Neural Networks With Residual Quantization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a stem-residual framework which provides new insight into Ternary quantization, termed Residual Quantization (TRQ), to achieve more powerful TNNs. |
Yue Li; Wenrui Ding; Chunlei Liu; Baochang Zhang; Guodong Guo; |
| 15 | Contrastive Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. |
Yunfan Li; Peng Hu; Zitao Liu; Dezhong Peng; Joey Tianyi Zhou; Xi Peng; |
| 16 | Longitudinal Deep Kernel Gaussian Process Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Longitudinal deep kernel Gaussian process regression (L-DKGPR) to overcome these limitations by fully automating the discovery of complex multilevel correlation structure from longitudinal data. |
Junjie Liang; Yanting Wu; Dongkuan Xu; Vasant G Honavar; |
| 17 | Large Norms of CNN Layers Do Not Hurt Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on our theorem, we propose a novel regularization method termed norm decay, which can effectively reduce the norms of convolutional layers and fully-connected layers. |
Youwei Liang; Dong Huang; |
| 18 | Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this challenge, in this paper we propose doubly residual neural (DRN) decoder. |
Siyu Liao; Chunhua Deng; Miao Yin; Bo Yuan; |
| 19 | From Label Smoothing to Label Relaxation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an alternative, we propose a generalized technique called label relaxation, in which the target is a set of probabilities represented in terms of an upper probability distribution. |
Julian Lienen; Eyke Hüllermeier; |
| 20 | Sample Selection for Universal Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a scoring scheme that is effective in identifying the samples of the shared classes. |
Omri Lifshitz; Lior Wolf; |
| 21 | Class-Attentive Diffusion Network for Semi-Supervised Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Adaptive aggregation with Class-Attentive Diffusion (AdaCAD), a new aggregation scheme that adaptively aggregates nodes probably of the same class among K-hop neighbors. |
Jongin Lim; Daeho Um; Hyung Jin Chang; Dae Ung Jo; Jin Young Choi; |
| 22 | Auto-Encoding Transformations in Reparameterized Lie Groups for Unsupervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Particularly, we focus on homographies, a general group of planar transformations containing the Euclidean, similarity and affine transformations as its special cases. |
Feng Lin; Haohang Xu; Houqiang Li; Hongkai Xiong; Guo-Jun Qi; |
| 23 | Multi-Proxy Wasserstein Classifier for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we adopt optimal transport theory to calculate a non-uniform matching flow between the elements in the feature map of a sample and the proxies of a class in a closed way. |
Benlin Liu; Yongming Rao; Jiwen Lu; Jie Zhou; Cho-Jui Hsieh; |
| 24 | TransTailor: Pruning The Pre-trained Model for Improved Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose TransTailor, targeting at pruning the pre-trained model for improved transfer learning. |
Bingyan Liu; Yifeng Cai; Yao Guo; Xiangqun Chen; |
| 25 | Learning A Few-shot Embedding Model with Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The objective of this paper is to repurpose the contrastive learning for such matching to learn a few-shot embedding model. |
Chen Liu; Yanwei Fu; Chengming Xu; Siqian Yang; Jilin Li; Chengjie Wang; Li Zhang; |
| 26 | Unchain The Search Space with Hierarchical Differentiable Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level. |
Guanting Liu; Yujie Zhong; Sheng Guo; Matthew R. Scott; Weilin Huang; |
| 27 | Overcoming Catastrophic Forgetting in Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel scheme dedicated to overcoming catastrophic forgetting problem and hence strengthen continual learning in GNNs. |
Huihui Liu; Yiding Yang; Xinchao Wang; |
| 28 | Stable Adversarial Learning Under Distributional Shifts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target. |
Jiashuo Liu; Zheyan Shen; Peng Cui; Linjun Zhou; Kun Kuang; Bo Li; Yishi Lin; |
| 29 | Hierarchical Multiple Kernel Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a brief insight of the aforementioned issue and propose a hierarchical approach to perform clustering while preserving advantageous details maximumly. |
Jiyuan Liu; Xinwang Liu; Siwei Wang; Sihang Zhou; Yuexiang Yang; |
| 30 | Dynamically Grown Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method to dynamically grow a GAN during training, optimizing the network architecture and its parameters together with automation. |
Lanlan Liu; Yuting Zhang; Jia Deng; Stefano Soatto; |
| 31 | FLAME: Differentially Private Federated Learning in The Shuffle Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i.e., accuracy in the curator model and strong privacy without relying on any trusted party. |
Ruixuan Liu; Yang Cao; Hong Chen; Ruoyang Guo; Masatoshi Yoshikawa; |
| 32 | Post-training Quantization with Multiple Points: Mixed Precision Without Mixed Precision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number. |
Xingchao Liu; Mao Ye; Dengyong Zhou; Qiang Liu; |
| 33 | Train A One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. |
Yu Liu; Lianghua Huang; Pan Pan; Bin Wang; Yinghui Xu; Rong Jin; |
| 34 | ROSITA: Refined BERT COmpreSsion with InTegrAted Techniques Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Pre-trained language models of the BERT family have defined the state-of-the-arts in a wide range of NLP tasks. |
Yuanxin Liu; Zheng Lin; Fengcheng Yuan; |
| 35 | Task Aligned Generative Meta-learning for Zero-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this regard, we propose a novel Task-aligned Generative Meta-learning model for Zero-shot learning (TGMZ), aiming to mitigate the potentially biased training and to enable meta-ZSL to accommodate real-world datasets that contain diverse distributions. |
Zhe Liu; Yun Li; Lina Yao; Xianzhi Wang; Guodong Long; |
| 36 | Learning from EXtreme Bandit Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a selective importance sampling estimator (sIS) that operates in a significantly more favorable bias-variance regime. |
Romain Lopez; Inderjit S. Dhillon; Michael I. Jordan; |
| 37 | Improving Causal Discovery By Optimal Bayesian Network Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that optimal score-based exhaustive search is remarkably useful for causal discovery: it requires weaker conditions to guarantee asymptotic correctness, and outperforms well-known methods including PC, GES, GSP, and NOTEARS. |
Ni Y Lu; Kun Zhang; Changhe Yuan; |
| 38 | Stochastic Graphical Bandits with Adversarial Corruptions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study graphical bandits with a reward model that interpolates between the two extremes, where the rewards are overall stochastically generated but a small fraction of them can be adversarially corrupted. |
Shiyin Lu; Guanghui Wang; Lijun Zhang; |
| 39 | Stochastic Bandits with Graph Feedback in Non-Stationary Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we study stochastic bandits with graph feedback in non-stationary environments and propose algorithms with graph-dependent dynamic regret bounds. |
Shiyin Lu; Yao Hu; Lijun Zhang; |
| 40 | Decentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper deals with distributed reinforcement learning problems with safety constraints. |
Songtao Lu; Kaiqing Zhang; Tianyi Chen; Tamer Başar; Lior Horesh; |
| 41 | Tailoring Embedding Function to Heterogeneous Few-Shot Tasks By Global and Local Feature Adaptors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Global and Local Feature Adaptor (GLoFA), a unifying framework that tailors the instance representation to specific tasks by global and local feature adaptors. |
Su Lu; Han-Jia Ye; De-Chuan Zhan; |
| 42 | PULNS: Positive-Unlabeled Learning with Effective Negative Sample Selector Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel PU learning approach dubbed PULNS, equipped with an effective negative sample selector, which is optimized by reinforcement learning. |
Chuan Luo; Pu Zhao; Chen Chen; Bo Qiao; Chao Du; Hongyu Zhang; Wei Wu; Shaowei Cai; Bing He; Saravanakumar Rajmohan; Qingwei Lin; |
| 43 | Revisiting Co-Occurring Directions: Sharper Analysis and Efficient Algorithm for Sparse Matrices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a tighter error bound for COD whose leading term considers the potential approximate low-rank structure and the correlation of input matrices. |
Luo Luo; Cheng Chen; Guangzeng Xie; Haishan Ye; |
| 44 | Semi-supervised Medical Image Segmentation Through Dual-task Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. |
Xiangde Luo; Jieneng Chen; Tao Song; Guotai Wang; |
| 45 | Adaptive Knowledge Driven Regularization for Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explicitly take into account the interaction between connected neurons, and propose an adaptive internal knowledge driven regularization method, CORR-Reg. |
Zhaojing Luo; Shaofeng Cai; Can Cui; Beng Chin Ooi; Yang Yang; |
| 46 | Multi-Domain Multi-Task Rehearsal for Lifelong Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased … |
Fan Lyu; Shuai Wang; Wei Feng; Zihan Ye; Fuyuan Hu; Song Wang; |
| 47 | On The Adequacy of Untuned Warmup for Adaptive Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we refute this analysis and provide an alternative explanation for the necessity of warmup based on the magnitude of the update term, which is of greater relevance to training stability. |
Jerry Ma; Denis Yarats; |
| 48 | Learning Representations for Incomplete Time Series Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper pro- poses a novel unsupervised temporal representation learning model, named Clustering Representation Learning on Incom- plete time-series data (CRLI). |
Qianli Ma; Chuxin Chen; Sen Li; Garrison W. Cottrell; |
| 49 | Joint-Label Learning By Dual Augmentation for Time Series Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Joint-label learning by Dual Augmentation (JobDA), which can enrich the training samples without expanding the distribution of the original data. |
Qianli Ma; Zhenjing Zheng; Jiawei Zheng; Sen Li; Wanqing Zhuang; Garrison W. Cottrell; |
| 50 | Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an unsupervised approach, coined OTCoarsening, with the use of optimal transport. |
Tengfei Ma; Jie Chen; |
| 51 | Sequential Attacks on Kalman Filter-based Forward Collision Warning Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study adversarial attacks on KF as part of the more complex machine-human hybrid system of Forward Collision Warning. |
Yuzhe Ma; Jon A Sharp; Ruizhe Wang; Earlence Fernandes; Xiaojin Zhu; |
| 52 | Exact Reduction of Huge Action Spaces in General Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we address the large action-space problem by sequentializing actions, which can reduce the action-space size significantly, even down to two actions at the expense of an increased planning horizon. |
Sultan J. Majeed; Marcus Hutter; |
| 53 | Composite Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of 32 base attackers. |
Xiaofeng Mao; Yuefeng Chen; Shuhui Wang; Hang Su; Yuan He; Hui Xue; |
| 54 | Deep Mutual Information Maximin for Cross-Modal Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel deep mutual information maximin (DMIM) method for cross-modal clustering is proposed to maximally preserve the shared information of multiple modalities while eliminating the superfluous information of individual modalities in an end-to-end manner. |
Yiqiao Mao; Xiaoqiang Yan; Qiang Guo; Yangdong Ye; |
| 55 | Searching for Machine Learning Pipelines Using A Context-Free Grammar Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take a different approach and focus on generating and optimizing pipelines of complex directed acyclic graph shapes. |
Radu Marinescu; Akihiro Kishimoto; Parikshit Ram; Ambrish Rawat; Martin Wistuba; Paulito P. Palmes; Adi Botea; |
| 56 | Scalable Graph Networks for Particle Simulations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we introduce an approach that transforms a fully-connected interaction graph into a hierarchical one which reduces the number of edges to O(N). |
Karolis Martinkus; Aurelien Lucchi; Nathanaël Perraudin; |
| 57 | Infinite Gaussian Mixture Modeling with An Improved Estimation of The Number of Clusters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The current paper shows that the nature of this inconsistency is an overestimation, and we pinpoint that this problem is an inherent part of the training algorithm. |
Avi Matza; Yuval Bistritz; |
| 58 | Exacerbating Algorithmic Bias Through Fairness Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose new types of data poisoning attacks where an adversary intentionally targets the fairness of a system. |
Ninareh Mehrabi; Muhammad Naveed; Fred Morstatter; Aram Galstyan; |
| 59 | Physarum Powered Differentiable Linear Programming Layers and Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an efficient and differentiable solver for general linear programming problems which can be used in a plug and play manner within deep neural networks as a layer. |
Zihang Meng; Sathya N. Ravi; Vikas Singh; |
| 60 | Lenient Regret for Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. |
Nadav Merlis; Shie Mannor; |
| 61 | Policy Optimization As Online Learning with Mediator Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose an algorithm, RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST), for regret minimization in PO, that employs a randomized exploration strategy, differently from the existing optimistic approaches. |
Alberto Maria Metelli; Matteo Papini; Pierluca D’Oro; Marcello Restelli; |
| 62 | Consistency and Finite Sample Behavior of Binary Class Probability Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: One of our core contributions is a novel way to derive finite sample L1-convergence rates of this estimator for different surrogate loss functions. |
Alexander Mey; Marco Loog; |
| 63 | Discovering Fully Oriented Causal Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To efficiently discover causal networks in practice, we introduce the GLOBE algorithm, which greedily adds, removes, and orients edges such that it minimizes the overall cost. |
Osman A Mian; Alexander Marx; Jilles Vreeken; |
| 64 | Generative Semi-supervised Learning for Multivariate Time Series Imputation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel semi-supervised generative adversarial network model, named SSGAN, for missing value imputation in multivariate time series data. |
Xiaoye Miao; Yangyang Wu; Jun Wang; Yunjun Gao; Xudong Mao; Jianwei Yin; |
| 65 | A General Class of Transfer Learning Regression Without Implementation Cost Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel framework that unifies and extends existing methods of transfer learning (TL) for regression. |
Shunya Minami; Song Liu; Stephen Wu; Kenji Fukumizu; Ryo Yoshida; |
| 66 | Scheduling of Time-Varying Workloads Using Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Deep Reinforcement Learning (DRL) based approach to exploit various temporal resource usage patterns of time varying workloads as well as a technique for creating equivalence classes among a large number of production workloads to improve scalability of our method. |
Shanka Subhra Mondal; Nikhil Sheoran; Subrata Mitra; |
| 67 | Improved Mutual Information Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to estimate the KL divergence using a relaxed likelihood ratio estimation in a Reproducing Kernel Hilbert space. |
Youssef Mroueh; Igor Melnyk; Pierre Dognin; Jarret Ross; Tom Sercu; |
| 68 | Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we examine the problem of infusing RL agents with commonsense knowledge. |
Keerthiram Murugesan; Mattia Atzeni; Pavan Kapanipathi; Pushkar Shukla; Sadhana Kumaravel; Gerald Tesauro; Kartik Talamadupula; Mrinmaya Sachan; Murray Campbell; |
| 69 | Task-Agnostic Exploration Via Policy Gradient of A Non-Parametric State Entropy Estimate Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that the entropy of the state distribution induced by finite-horizon trajectories is a sensible target. |
Mirco Mutti; Lorenzo Pratissoli; Marcello Restelli; |
| 70 | Elastic Consistency: A Practical Consistency Model for Distributed Stochastic Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a general consistency condition covering communication-reduced and asynchronous distributed SGD implementations. |
Giorgi Nadiradze; Ilia Markov; Bapi Chatterjee; Vyacheslav Kungurtsev; Dan Alistarh; |
| 71 | Game of Gradients: Mitigating Irrelevant Clients in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. |
Lokesh Nagalapatti; Ramasuri Narayanam; |
| 72 | Objective-Based Hierarchical Clustering of Deep Embedding Vectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to address the challenge of scaling up hierarchical clustering to such large datasets we propose a new practical hierarchical clustering algorithm B++&C. |
Stanislav Naumov; Grigory Yaroslavtsev; Dmitrii Avdiukhin; |
| 73 | 5* Knowledge Graph Embeddings with Projective Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose a novel KGE model 5*E in projective geometry, which supports multiple simultaneous transformations — specifically inversion, reflection, translation, rotation, and homothety. |
Mojtaba Nayyeri; Sahar Vahdati; Can Aykul; Jens Lehmann; |
| 74 | Advice-Guided Reinforcement Learning in A Non-Markovian Environment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we generalize both approaches and enable the user to give advice to the agent, representing the user’s best knowledge about the reward function, potentially fragmented, partial, or even incorrect. |
Daniel Neider; Jean-Raphael Gaglione; Ivan Gavran; Ufuk Topcu; Bo Wu; Zhe Xu; |
| 75 | Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To capture such dynamically changing asymmetric relationships between tasks in time-series data, we propose a novel temporal asymmetric multi-task learning model that performs knowledge transfer from certain tasks/timesteps to relevant uncertain tasks, based on the feature-level uncertainty. |
A. Tuan Nguyen; Hyewon Jeong; Eunho Yang; Sung Ju Hwang; |
| 76 | Modular Graph Transformer Networks for Multi-Label Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a multi-label image classification framework based on graph transformer networks to fully exploit inter-label interactions. |
Hoang D. Nguyen; Xuan-Son Vu; Duc-Trong Le; |
| 77 | Differentially Private K-Means Via Exponential Mechanism and Max Cover Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new (ϵₚ, δₚ)-differentially private algorithm for the k-means clustering problem. |
Huy L. Nguyen; Anamay Chaturvedi; Eric Z Xu; |
| 78 | Minimum Robust Multi-Submodular Cover for Fairness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study a novel problem, Minimum Robust Multi-Submodular Cover for Fairness (MinRF), as follows: given a ground set V; m monotone submodular functions f_1,…,f_m; m thresholds T_1,…,T_m and a non-negative integer r; MinRF asks for the smallest set S such that f_i(S \ X) ≥ T_i for all i ∈ [m] and |X| ≤ r. |
Lan N. Nguyen; My T. Thai; |
| 79 | Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel temporal latent auto-encoder method which enables nonlinear factorization of multivariate time series, learned end-to-end with a temporal deep learning latent space forecast model. |
Nam Nguyen; Brian Quanz; |
| 80 | An Information-Theoretic Framework for Unifying Active Learning Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant. |
Quoc Phong Nguyen; Bryan Kian Hsiang Low; Patrick Jaillet; |
| 81 | Top-k Ranking Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel approach to top-k ranking Bayesian optimization (top-k ranking BO) which is a practical and significant generalization of preferential BO to handle top-k ranking and tie/indifference observations. |
Quoc Phong Nguyen; Sebastian Tay; Bryan Kian Hsiang Low; Patrick Jaillet; |
| 82 | Distributional Reinforcement Learning Via Moment Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-art methods that estimate the distribution, as opposed to only the expectation, of the total return. |
Thanh Nguyen-Tang; Sunil Gupta; Svetha Venkatesh; |
| 83 | Precision-based Boosting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a generic refinement of all of these AdaBoost variants. |
Mohammad Hossein Nikravan; Marjan Movahedan; Sandra Zilles; |
| 84 | Improving Model Robustness By Adaptively Correcting Perturbation Levels with Active Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. |
Kun-Peng Ning; Lue Tao; Songcan Chen; Sheng-Jun Huang; |
| 85 | Learning of Structurally Unambiguous Probabilistic Grammars Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we address the first problem. |
Dolav Nitay; Dana Fisman; Michal Ziv-Ukelson; |
| 86 | RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes RT3D, a model compression and mobile acceleration framework for 3D CNNs, seamlessly integrating neural network weight pruning and compiler code generation techniques. |
Wei Niu; Mengshu Sun; Zhengang Li; Jou-An Chen; Jiexiong Guan; Xipeng Shen; Yanzhi Wang; Sijia Liu; Xue Lin; Bin Ren; |
| 87 | Warm Starting CMA-ES for Hyperparameter Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to transfer prior knowledge on similar HPO tasks through the initialization of the CMA-ES, leading to significantly shortening the adaptation time. |
Masahiro Nomura; Shuhei Watanabe; Youhei Akimoto; Yoshihiko Ozaki; Masaki Onishi; |
| 88 | Inverse Reinforcement Learning From Like-Minded Teachers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of learning a policy in a Markov decision process (MDP) based on observations of the actions taken by multiple teachers. |
Ritesh Noothigattu; Tom Yan; Ariel D. Procaccia; |
| 89 | Multinomial Logit Contextual Bandits: Provable Optimality and Practicality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose upper confidence bound based algorithms for this MNL contextual bandit. |
Min-hwan Oh; Garud Iyengar; |
| 90 | Learning Deep Generative Models for Queuing Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel data-driven approach towards queuing systems: the Deep Generative Service Times. |
Cesar Ojeda; Kostadin Cvejoski; Bodgan Georgiev; Christian Bauckhage; Jannis Schuecker; Ramses J. Sanchez; |
| 91 | OT-Flow: Fast and Accurate Continuous Normalizing Flows Via Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our proposed OT-Flow approach tackles two critical computational challenges that limit a more widespread use of CNFs. |
Derek Onken; Samy Wu Fung; Xingjian Li; Lars Ruthotto; |
| 92 | FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a novel learning architecture that achieves performance competitive with or better than the best existing algorithms, without requiring knowledge of the graph. |
Boris N. Oreshkin; Arezou Amini; Lucy Coyle; Mark Coates; |
| 93 | Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work provides positive evidence to this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. |
Boris N. Oreshkin; Dmitri Carpov; Nicolas Chapados; Yoshua Bengio; |
| 94 | Augmented Experiment in Material Engineering Using Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an approach combining empirical data and domain analytical models to reduce the number of real experiments required to obtain the desired synthesis. |
Aomar Osmani; Massinissa Hamidi; Salah Bouhouche; |
| 95 | Second Order Techniques for Learning Time-series with Structural Breaks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study fundamental problems in learning nonstationary time-series: how to effectively regularize time-series models and how to adaptively tune forgetting rates. |
Takayuki Osogami; |
| 96 | Defending Against Backdoors in Federated Learning with Robust Learning Rate Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To prevent backdoor attacks, we propose a lightweight defense that requires minimal change to the FL protocol. |
Mustafa Safa Ozdayi; Murat Kantarcioglu; Yulia R. Gel; |
| 97 | Robustness Guarantees for Mode Estimation with An Application to Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we give precise robustness guarantees as well as privacy guarantees under simple randomization. |
Aldo Pacchiano; Heinrich Jiang; Michael I. Jordan; |
| 98 | Disentangled Information Bottleneck Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we implement the IB method from the perspective of supervised disentangling. |
Ziqi Pan; Li Niu; Jianfu Zhang; Liqing Zhang; |
| 99 | NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to analyze the architecture transferability of different NAS methods by performing a series of experiments on large scale benchmarks such as ImageNet1K and ImageNet22K. |
Rameswar Panda; Michele Merler; Mayoore S Jaiswal; Hui Wu; Kandan Ramakrishnan; Ulrich Finkler; Chun-Fu Richard Chen; Minsik Cho; Rogerio Feris; David Kung; Bishwaranjan Bhattacharjee; |
| 100 | Robust Reinforcement Learning: A Case Study in Linear Quadratic Regulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we revisit the benchmark problem of discrete-time linear quadratic regulation (LQR) and study the long-standing open question: Under what conditions is the policy iteration method robustly stable from a dynamical systems perspective? |
Bo Pang; Zhong-Ping Jiang; |
| 101 | Tempered Sigmoid Activations for Deep Learning with Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve these tradeoffs, prior work introduces variants of differential privacy that weaken the privacy guarantee proved to increase model utility. |
Nicolas Papernot; Abhradeep Thakurta; Shuang Song; Steve Chien; Úlfar Erlingsson; |
| 102 | Vector Quantized Bayesian Neural Network Inference for Data Streams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel model VQ-BNN, which approximates BNN inference for data streams. |
Namuk Park; Taekyu Lee; Songkuk Kim; |
| 103 | Maximum Roaming Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a novel way to partition the parameter space without weakening the inductive bias. |
Lucas Pascal; Pietro Michiardi; Xavier Bost; Benoit Huet; Maria A. Zuluaga; |
| 104 | Fast PCA in 1-D Wasserstein Spaces Via B-splines Representation and Metric Projection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel representation of the 2-Wasserstein space, based on a well known isometric bijection and a B-spline expansion. |
Matteo Pegoraro; Mario Beraha; |
| 105 | AutoDropout: Learning Dropout Patterns to Regularize Deep Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose to learn the dropping patterns. |
Hieu Pham; Quoc Le; |
| 106 | Fast Multi-view Discrete Clustering with Anchor Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose Fast Multi-view Discrete Clustering (FMDC) with anchor graphs, focusing on directly solving the spectral clustering problem with a small time cost. |
Qianyao Qiang; Bin Zhang; Fei Wang; Feiping Nie; |
| 107 | Relation-aware Graph Attention Model with Adaptive Self-adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes an end-to-end solution for the relationship prediction task in heterogeneous, multi-relational graphs. |
Xiao Qin; Nasrullah Sheikh; Berthold Reinwald; Lingfei Wu; |
| 108 | Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop techniques to control the uncertainty introduced by these estimates. |
James Queeney; Ioannis Ch. Paschalidis; Christos G. Cassandras; |
| 109 | Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop a new approach to temporal max pooling that makes the required memory invariant to the sequence length T. |
Edward Raff; William Fleshman; Richard Zak; Hyrum S. Anderson; Bobby Filar; Mark McLean; |
| 110 | Online DR-Submodular Maximization: Minimizing Regret and Constraint Violation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider online continuous DR-submodular maximization with linear stochastic long-term constraints. |
Prasanna Raut; Omid Sadeghi; Maryam Fazel; |
| 111 | Improving Generative Moment Matching Networks with Distribution Partition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new strategy to train GMMN with a low sample complexity while retaining the theoretical soundness. |
Yong Ren; Yucen Luo; Jun Zhu; |
| 112 | Multiple Kernel Clustering with Kernel K-Means Coupled Graph Tensor Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel method, kernel k-means coupled graph tensor (KCGT), is proposed to graciously couple KKM and SC for seizing their merits and evading their demerits simultaneously. |
Zhenwen Ren; Quansen Sun; Dong Wei; |
| 113 | Robust Fairness Under Covariate Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach that obtains the predictor that is robust to the worst-case testing performance while satisfying target fairness requirements and matching statistical properties of the source data. |
Ashkan Rezaei; Anqi Liu; Omid Memarrast; Brian D. Ziebart; |
| 114 | Shuffling Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel recurrent neural network model, where the hidden state hₜ is obtained by permuting the vector elements of the previous hidden state hₜ₋₁ and adding the output of a learned function β(xₜ) of the input xₜ at time t. |
Michael Rotman; Lior Wolf; |
| 115 | Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we establish the involvement of Turing instability to create such patterns. |
Litu Rout; |
| 116 | Adversarial Permutation Guided Node Representations for Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we propose PermGNN, which aggregates neighbor features using a recurrent, order-sensitive aggregator and directly minimizes an LP loss while it is `attacked’ by adversarial generator of neighbor permutations. |
Indradyumna Roy; Abir De; Soumen Chakrabarti; |
| 117 | Visual Transfer For Reinforcement Learning Via Wasserstein Domain Confusion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. |
Josh Roy; George D. Konidaris; |
| 118 | Anytime Inference with Distilled Hierarchical Neural Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers. |
Adria Ruiz; Jakob Verbeek; |
| 119 | Inverse Reinforcement Learning with Explicit Policy Estimates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we make previously unknown connections between these related methods from both fields. |
Navyata Sanghvi; Shinnosuke Usami; Mohit Sharma; Joachim Groeger; Kris Kitani; |
| 120 | A Deeper Look at The Hessian Eigenspectrum of Deep Neural Networks and Its Applications to Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is studied independently and also on how each correlates to the overall loss surface. |
Adepu Ravi Sankar; Yash Khasbage; Rahul Vigneswaran; Vineeth N Balasubramanian; |
| 121 | AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel search strategy for one-shot and sparse propagation NAS, namely AdvantageNAS, which further reduces the time complexity of NAS by reducing the number of search iterations. |
Rei Sato; Jun Sakuma; Youhei Akimoto; |
| 122 | Active Feature Selection for The Mutual Information Criterion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explain and experimentally study the choices that we make in the algorithm, and show that they lead to a successful algorithm, compared to other more naive approaches. |
Shachar Schnapp; Sivan Sabato; |
| 123 | Learning Precise Temporal Point Event Detection with Misaligned Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in an attempt to overcome these shortcomings, we introduce a simple and versatile training paradigm combining soft localization learning with counting-based sparsity regularization. |
Julien Schroeter; Kirill Sidorov; David Marshall; |
| 124 | Multi-type Disentanglement Without Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a unified distribution-controlling method, which provides each specific style value (the value of style types, e.g., positive sentiment, or past tense) with a unique representation. |
Lei Sha; Thomas Lukasiewicz; |
| 125 | Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework. |
Uday Shankar Shanthamallu; Jayaraman J. Thiagarajan; Andreas Spanias; |
| 126 | Right for Better Reasons: Training Differentiable Models By Constraining Their Influence Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Explaining black-box models such as deep neural networks is becoming increasingly important as it helps to boost trust and debugging. |
Xiaoting Shao; Arseny Skryagin; Wolfgang Stammer; Patrick Schramowski; Kristian Kersting; |
| 127 | Meta-Learning Effective Exploration Strategies for Contextual Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop a meta-learning algorithm, Mêlée, that learns an exploration policy based on simulated, synthetic con- textual bandit tasks. |
Amr Sharaf; Hal Daumé III; |
| 128 | Membership Privacy for Machine Learning Models Through Knowledge Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work proposes a new defense, called distillation for membership privacy (DMP), against MIAs that preserves the utility of the resulting models significantly better than prior defenses. |
Virat Shejwalkar; Amir Houmansadr; |
| 129 | Theoretically Principled Deep RL Acceleration Via Nearest Neighbor Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present (1) Nearest Neighbor Actor-Critic (NNAC), an online policy gradient algorithm that demonstrates the practicality of combining function approximation with deep RL, and (2) a plug-and-play NN update module that aids the training of existing deep RL methods. |
Junhong Shen; Lin F. Yang; |
| 130 | Time Series Anomaly Detection with Multiresolution Ensemble Decoding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple yet efficient recurrent network ensemble called Recurrent Autoencoder with Multiresolution Ensemble Decoding (RAMED). |
Lifeng Shen; Zhongzhong Yu; Qianli Ma; James T. Kwok; |
| 131 | STL-SGD: Speeding Up Local SGD with Stagewise Communication Period Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to accelerate the convergence by reducing the communication complexity, we propose STagewise Local SGD (STL-SGD), which increases the communication period gradually along with decreasing learning rate. |
Shuheng Shen; Yifei Cheng; Jingchang Liu; Linli Xu; |
| 132 | PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use partial differential operators (PDOs) to design a spherical equivariant CNN, PDO-eS2CNN, which is exactly rotation equivariant in the continuous domain. |
Zhengyang Shen; Tiancheng Shen; Zhouchen Lin; Jinwen Ma; |
| 133 | Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to transfer partial knowledge by freezing or fine-tuning particular layer(s) in the base model. |
Zhiqiang Shen; Zechun Liu; Jie Qin; Marios Savvides; Kwang-Ting Cheng; |
| 134 | Federated Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This model introduces a new uncertainty of client sampling, as the global model may not be reliably learned even if the finite local models are perfectly known. |
Chengshuai Shi; Cong Shen; |
| 135 | Raven’s Progressive Matrices Completion with Latent Gaussian Process Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables. |
Fan Shi; Bin Li; Xiangyang Xue; |
| 136 | Improved Penalty Method Via Doubly Stochastic Gradients for Bilevel Hyperparameter Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, in this paper, we propose a doubly stochastic gradient descent algorithm (DSGPHO) to improve the efficiency of the penalty method. |
Wanli Shi; Bin Gu; |
| 137 | Online Class-Incremental Continual Learning with Adversarial Shapley Value Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. |
Dongsub Shim; Zheda Mai; Jihwan Jeong; Scott Sanner; Hyunwoo Kim; Jongseong Jang; |
| 138 | Scalable Affinity Propagation for Massive Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel fast algorithm, ScaleAP, which outputs the same clusters as AP but within a shorter computation time. |
Hiroaki Shiokawa; |
| 139 | Interpretable Sequence Classification Via Discrete Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we learn sequence classifiers that favour early classification from an evolving observation trace. |
Maayan Shvo; Andrew C. Li; Rodrigo Toro Icarte; Sheila A. McIlraith; |
| 140 | Towards Domain Invariant Single Image Dehazing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we utilize an encoder-decoder based network architecture to perform the task of dehazing and integrate an spatially aware channel attention mechanism to enhance features of interest beyond the receptive field of traditional conventional kernels. |
Pranjay Shyam; Kuk-Jin Yoon; Kyung-Soo Kim; |
| 141 | DIBS: Diversity Inducing Information Bottleneck in Model Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. |
Samarth Sinha; Homanga Bharadhwaj; Anirudh Goyal; Hugo Larochelle; Animesh Garg; Florian Shkurti; |
| 142 | Differential Spectral Normalization (DSN) for PDE Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel and robust regularization method tailored for moment-constrained convolutional filters, namely, Differential Spectral Normalization (DSN), to allow accurate estimation of coefficient functions and stable prediction of dynamics in a long time horizon. |
Chi Chiu So; Tsz On Li; Chufang Wu; Siu Pang Yung; |
| 143 | UNIPoint: Universally Approximating Point Processes Intensities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using these insights, we design and implement UNIPoint, a novel neural point process model, using recurrent neural networks to parameterise sums of basis function upon each event. |
Alexander Soen; Alexander Mathews; Daniel Grixti-Cheng; Lexing Xie; |
| 144 | Solving Common-Payoff Games with Approximate Policy Iteration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes CAPI, a novel algorithm which, like BAD, combines common knowledge with deep reinforcement learning. |
Samuel Sokota; Edward Lockhart; Finbarr Timbers; Elnaz Davoodi; Ryan D’Orazio; Neil Burch; Martin Schmid; Michael Bowling; Marc Lanctot; |
| 145 | Improving Gradient Flow with Unrolled Highway Expectation Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Highway Expectation Maximization Networks (HEMNet), which is comprised of unrolled iterations of the generalized EM (GEM) algorithm based on the Newton-Rahpson method. |
Chonghyuk Song; Eunseok Kim; Inwook Shim; |
| 146 | Implicit Kernel Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: From this decomposition, we generalize the attention in three ways. |
Kyungwoo Song; Yohan Jung; Dongjun Kim; Il-Chul Moon; |
| 147 | Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an end-to-end training method for our ECNN, which allows further improvement of the diversity between binary classifiers. |
Yang Song; Qiyu Kang; Wee Peng Tay; |
| 148 | Hierarchical Relational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose a novel approach to physical reasoning that models objects as hierarchies of parts that may locally behave separately, but also act more globally as a single whole. |
Aleksandar Stanić; Sjoerd van Steenkiste; Jürgen Schmidhuber; |
| 149 | `Less Than One’-Shot Learning: Learning N Classes From M < N Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the ‘less than one’-shot learning task where models must learn N new classes given only M |
Ilia Sucholutsky; Matthias Schonlau; |
| 150 | HiABP: Hierarchical Initialized ABP for Unsupervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Hierarchical Initialized Alternating Back-propagation (HiABP) for efficient Bayesian inference. |
Jiankai Sun; Rui Liu; Bolei Zhou; |
| 151 | Stability and Generalization of Decentralized Stochastic Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a novel formulation of the decentralized stochastic gradient descent. |
Tao Sun; Dongsheng Li; Bao Wang; |
| 152 | TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present two algorithms for an “online” and a “finite-model” setting respectively. |
Yanchao Sun; Xiangyu Yin; Furong Huang; |
| 153 | PAC Learning of Causal Trees with Latent Variables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a polynomial-time algorithm that PAC learns the structure and parameters of a rooted tree-structured causal network of bounded degree where the internal nodes of the tree cannot be observed or manipulated. |
Prasad Tadepalli; Stuart J. Russell; |
| 154 | Learning Dynamics Models with Stable Invariant Sets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method to ensure that a dynamics model has a stable invariant set of general classes such as limit cycles and line attractors. |
Naoya Takeishi; Yoshinobu Kawahara; |
| 155 | Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we fill the gap by improving the upper and lower bounds. |
Kei Takemura; Shinji Ito; Daisuke Hatano; Hanna Sumita; Takuro Fukunaga; Naonori Kakimura; Ken-ichi Kawarabayashi; |
| 156 | Explicitly Modeled Attention Maps for Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a novel self-attention module with explicitly modeled attention-maps using only a single learnable parameter for low computational overhead. |
Andong Tan; Duc Tam Nguyen; Maximilian Dax; Matthias Nießner; Thomas Brox; |
| 157 | Proxy Graph Matching with Proximal Matching Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these issues, we propose a new learning-based matching framework, which is designed to be rotationally invariant. |
Hao-Ru Tan; Chuang Wang; Si-Tong Wu; Tie-Qiang Wang; Xu-Yao Zhang; Cheng-Lin Liu; |
| 158 | Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a robust representation of the firing rate to reduce the error during the conversion process. |
Weihao Tan; Devdhar Patel; Robert Kozma; |
| 159 | Empowering Adaptive Early-Exit Inference with Latency Awareness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Empirically, on top of various models across multiple datasets (CIFAR-10, CIFAR-100, ImageNet and two time-series datasets), we show that our method can well handle the average latency requirements, and consistently finds good threshold settings in negligible time. |
Xinrui Tan; Hongjia Li; Liming Wang; Xueqing Huang; Zhen Xu; |
| 160 | Foresee Then Evaluate: Decomposing Value Estimation with Latent Future Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Value Decomposition with Future Prediction (VDFP), providing an explicit two-step understanding of the value estimation process: 1) first foresee the latent future, 2) and then evaluate it. |
Hongyao Tang; Zhaopeng Meng; Guangyong Chen; Pengfei Chen; Chen Chen; Yaodong Yang; Luo Zhang; Wulong Liu; Jianye Hao; |
| 161 | Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We prove that GDA yields the optimal convergence rate in terms of output averaging, while SC-PDA derives the optimal individual convergence. |
Wei Tao; Wei Li; Zhisong Pan; Qing Tao; |
| 162 | Evolutionary Approach for AutoAugment Using The Thermodynamical Genetic Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we solved these problems by introducing evolutionary computation to previous methods. |
Akira Terauchi; Naoki Mori; |
| 163 | Semi-Supervised Knowledge Amalgamation for Sequence Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To achieve this, KA methods combine the knowledge of multiple pre-trained teacher models (trained on different classification tasks and proprietary datasets) into one student model that becomes an expert on the union of all teachers’ classes. |
Jidapa Thadajarassiri; Thomas Hartvigsen; Xiangnan Kong; Elke A Rundensteiner; |
| 164 | Online Non-Monotone DR-Submodular Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study fundamental problems of maximizing DR-submodular continuous functions that have real-world applications in the domain of machine learning, economics, operations research and communication systems. |
Nguyễn Kim Thắng; Abhinav Srivastav; |
| 165 | Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. |
Jinyu Tian; Jiantao Zhou; Yuanman Li; Jia Duan; |
| 166 | Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose an efficient yet general modelling approach for obtaining well-calibrated, trustworthy probabilities for samples obtained after a domain shift. |
Christian Tomani; Florian Buettner; |
| 167 | Meta Learning for Causal Direction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on distinguishing the cause from effect in the bivariate setting under limited observational data. |
Jean-François Ton; Dino Sejdinovic; Kenji Fukumizu; |
| 168 | Learning Compositional Sparse Gaussian Processes with A Shrinkage Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to the search-based approach, we present a novel probabilistic algorithm to learn a kernel composition by handling the sparsity in the kernel selection with Horseshoe prior. |
Anh Tong; Toan M Tran; Hung Bui; Jaesik Choi; |
| 169 | Characterizing Deep Gaussian Processes Via Nonlinear Recurrence Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new analysis in DGPs by studying its corresponding nonlinear dynamic systems to explain the issue. |
Anh Tong; Jaesik Choi; |
| 170 | Iterative Bounding MDPs: Learning Interpretable Policies Via Non-Interpretable Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we propose a novel Markov Decision Process (MDP) type for learning decision tree policies: Iterative Bounding MDPs (IBMDPs). |
Nicholay Topin; Stephanie Milani; Fei Fang; Manuela Veloso; |
| 171 | Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, this paper studies a model that protects the privacy of the individuals’ sensitive information while also allowing it to learn non-discriminatory predictors. |
Cuong Tran; Ferdinando Fioretto; Pascal Van Hentenryck; |
| 172 | Learning Adjustment Sets from Observational and Limited Experimental Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a method that combines large observational and limited experimental data to identify adjustment sets and improve the estimation of causal effects for a target population. |
Sofia Triantafillou; Greg Cooper; |
| 173 | *-CFQ: Analyzing The Scalability of Machine Learning on A Compositional Task Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional task setting. |
Dmitry Tsarkov; Tibor Tihon; Nathan Scales; Nikola Momchev; Danila Sinopalnikov; Nathanael Schärli; |
| 174 | Toward Robust Long Range Policy Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method, which leverages the hierarchical structure to train the combination function and adapt the set of diverse primitive polices alternatively, to efficiently produce a range of complex behaviors on challenging new tasks. |
Wei-Cheng Tseng; Jin-Siang Lin; Yao-Min Feng; Min Sun; |
| 175 | Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that unlike some previously studied neural network kernels, these new kernels exhibit non-trivial fixed-point dynamics which are mirrored in finite-width neural networks. |
Russell Tsuchida; Tim Pearce; Chris van der Heide; Fred Roosta; Marcus Gallagher; |
| 176 | Deep Fusion Clustering Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the above issues, we propose a Deep Fusion Clustering Network (DFCN). |
Wenxuan Tu; Sihang Zhou; Xinwang Liu; Xifeng Guo; Zhiping Cai; En Zhu; Jieren Cheng; |
| 177 | ESCAPED: Efficient Secure and Private Dot Product Framework for Kernel-based Machine Learning Algorithms with Applications in Healthcare Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this problem by introducing ESCAPED, which stands for Efficient SeCure And PrivatE Dot product framework. |
Ali Burak Ünal; Mete Akgün; Nico Pfeifer; |
| 178 | Expected Eligibility Traces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce expected eligibility traces. |
Hado van Hasselt; Sephora Madjiheurem; Matteo Hessel; David Silver; André Barreto; Diana Borsa; |
| 179 | Continual General Chunking Problem and SyncMap Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations. |
Danilo Vasconcellos Vargas; Toshitake Asabuki; |
| 180 | Gated Linear Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). |
Joel Veness; Tor Lattimore; David Budden; Avishkar Bhoopchand; Christopher Mattern; Agnieszka Grabska-Barwinska; Eren Sezener; Jianan Wang; Peter Toth; Simon Schmitt; Marcus Hutter; |
| 181 | GraphMix: Improved Training of GNNs for Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization. |
Vikas Verma; Meng Qu; Kenji Kawaguchi; Alex Lamb; Yoshua Bengio; Juho Kannala; Jian Tang; |
| 182 | PID-Based Approach to Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the classic proportional-integral-derivative (PID) controller in the field of automatic control, we propose a new PID-based approach for generating adversarial examples. |
Chen Wan; Biaohua Ye; Fangjun Huang; |
| 183 | Nearest Neighbor Classifier Embedded Network for Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to replace the softmax classifier in deep neural network with a nearest neighbor classifier, considering its progressive generalization ability within the unknown sub-space. |
Fang Wan; Tianning Yuan; Mengying Fu; Xiangyang Ji; Qingming Huang; Qixiang Ye; |
| 184 | Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To accommodate this issue, this paper presents a novel GCN-based SSL algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure. |
Sheng Wan; Shirui Pan; Jian Yang; Chen Gong; |
| 185 | Approximate Multiplication of Sparse Matrices with Limited Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to reduce the time complexity by exploiting the sparsity of the input matrices. |
Yuanyu Wan; Lijun Zhang; |
| 186 | Projection-free Online Learning in Dynamic Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, without the condition of the smoothness, we propose a novel projection-free online algorithm, and achieve an O(max{T^{2/3}V_T^{1/3},T^{1/2}}) dynamic regret bound for convex functions and an O(max{(TV_Tlog T)^{1/2},log T}) dynamic regret bound for strongly convex functions, where T is the time horizon and V_T denotes the variation of loss functions. |
Yuanyu Wan; Bo Xue; Lijun Zhang; |
| 187 | Projection-free Online Learning Over Strongly Convex Sets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that it achieves a regret bound of O(T^{2/3}) over general convex sets and a better regret bound of O(T^{1/2}) over strongly convex sets. |
Yuanyu Wan; Lijun Zhang; |
| 188 | Multi-View Information-Bottleneck Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel and flexible unsupervised multi-view representation learning model termed Collaborative Multi-View Information Bottleneck Networks (CMIB-Nets), which comprehensively explores the common latent structure and the view-specific intrinsic information, and discards the superfluous information in the data significantly improving the generalization capability of the model. |
Zhibin Wan; Changqing Zhang; Pengfei Zhu; Qinghua Hu; |
| 189 | Semi-Supervised Node Classification on Graphs: Markov Random Fields Vs. Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to address the key limitation of existing pMRF-based methods. |
Binghui Wang; Jinyuan Jia; Neil Zhenqiang Gong; |
| 190 | Quantum Exploration Algorithms for Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we provide an algorithm to find the best arm with fixed confidence based on variable-time amplitude amplification and estimation. |
Daochen Wang; Xuchen You; Tongyang Li; Andrew M. Childs; |
| 191 | Learning from Noisy Labels with Complementary Loss Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a general framework to learn robust deep neural networks with complementary loss functions. |
Deng-Bao Wang; Yong Wen; Lujia Pan; Min-Ling Zhang; |
| 192 | Debiasing Evaluations That Are Biased By Evaluations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we call these external factors the "outcome" experienced by people, and consider the problem of mitigating these outcome-induced biases in the given ratings when some information about the outcome is available. |
Jingyan Wang; Ivan Stelmakh; Yuting Wei; Nihar B. Shah; |
| 193 | Enhancing Unsupervised Video Representation Learning By Decoupling The Scene and The Motion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid. |
Jinpeng Wang; Yuting Gao; Ke Li; Jianguo Hu; Xinyang Jiang; Xiaowei Guo; Rongrong Ji; Xing Sun; |
| 194 | Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a bidirectional style-induced domain adaptation method, called BiSIDA, that employs consistency regularization to efficiently exploit information from the unlabeled target domain dataset, requiring only a simple neural style transfer model. |
Kaihong Wang; Chenhongyi Yang; Margrit Betke; |
| 195 | Embedding Heterogeneous Networks Into Hyperbolic Space Without Meta-path Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel self-guided random walk method that does not require meta-path for embedding heterogeneous networks into hyperbolic space. |
Lili Wang; Chongyang Gao; Chenghan Huang; Ruibo Liu; Weicheng Ma; Soroush Vosoughi; |
| 196 | Adversarial Linear Contextual Bandits with Graph-Structured Side Observations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: contexts and side observations. |
Lingda Wang; Bingcong Li; Huozhi Zhou; Georgios B. Giannakis; Lav R. Varshney; Zhizhen Zhao; |
| 197 | Addressing Class Imbalance in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a monitoring scheme that can infer the composition of training data for each FL round, and design a new loss function — Ratio Loss to mitigate the impact of the imbalance. |
Lixu Wang; Shichao Xu; Xiao Wang; Qi Zhu; |
| 198 | Contrastive Transformation for Self-supervised Correspondence Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. |
Ning Wang; Wengang Zhou; Houqiang Li; |
| 199 | Tackling Instance-Dependent Label Noise Via A Universal Probabilistic Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. |
Qizhou Wang; Bo Han; Tongliang Liu; Gang Niu; Jian Yang; Chen Gong; |
| 200 | Learning with Group Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this issue, we propose a novel Max-Matching method for learning with group noise. |
Qizhou Wang; Jiangchao Yao; Chen Gong; Tongliang Liu; Mingming Gong; Hongxia Yang; Bo Han; |
| 201 | Adaptive Verifiable Training Using Pairwise Class Similarity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new approach that utilizes inter-class similarity to improve the performance of verifiable training and create robust models with respect to multiple adversarial criteria. |
Shiqi Wang; Kevin Eykholt; Taesung Lee; Jiyong Jang; Ian Molloy; |
| 202 | Adaptive Algorithms for Multi-armed Bandit with Composite and Anonymous Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose adaptive algorithms for both the stochastic and the adversarial cases, without requiring any prior information about the reward interval. |
Siwei Wang; Haoyun Wang; Longbo Huang; |
| 203 | Harmonized Dense Knowledge Distillation Training for Multi-Exit Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel Harmonized Dense Knowledge Distillation (HDKD) training method for multi-exit architecture is designed to encourage each exit to flexibly learn from all its later exits. |
Xinglu Wang; Yingming Li; |
| 204 | Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Tied Block Convolution (TBC) that shares the same thinner filter over equal blocks of channels and produces multiple responses with a single filter. |
Xudong Wang; Stella X. Yu; |
| 205 | Deep Recurrent Belief Propagation Network for POMDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new method that lies somewhere in the middle of the spectrum of research methodology identified above and combines the strength of both approaches. |
Yuhui Wang; Xiaoyang Tan; |
| 206 | Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a novel data-free KD approach by modeling the intermediate feature space of the teacher with a multivariate normal distribution and leveraging the soft targeted labels generated by the distribution to synthesize pseudo samples as the transfer set. |
Zi Wang; |
| 207 | Incremental Embedding Learning Via Zero-Shot Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI), which leverages zero-shot translation to estimate and compensate the semantic gap without any exemplars. |
Kun Wei; Cheng Deng; Xu Yang; Maosen Li; |
| 208 | Gene Regulatory Network Inference As Relaxed Graph Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In an effort to better estimate regulatory networks from their noisy projections, we formulate a non-convex but analytically tractable optimization problem called OTTER. |
Deborah Weighill; Marouen Ben Guebila; Camila Lopes-Ramos; Kimberly Glass; John Quackenbush; John Platig; Rebekka Burkholz; |
| 209 | Unified Tensor Framework for Incomplete Multi-view Clustering and Missing-view Inferring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method, referred to as incomplete multi-view tensor spectral clustering with missing-view inferring (IMVTSC-MVI) to address the challenging multi-view clustering problem with missing views. |
Jie Wen; Zheng Zhang; Zhao Zhang; Lei Zhu; Lunke Fei; Bob Zhang; Yong Xu; |
| 210 | Learning Set Functions That Are Sparse in Non-Orthogonal Fourier Bases Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a new family of algorithms for learning Fourier-sparse set functions. |
Chris Wendler; Andisheh Amrollahi; Bastian Seifert; Andreas Krause; Markus Püschel; |
| 211 | BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we give a thorough analysis of the "BO + neural predictor framework" by identifying five main components: the architecture encoding, neural predictor, uncertainty calibration method, acquisition function, and acquisition function optimization. |
Colin White; Willie Neiswanger; Yash Savani; |
| 212 | Peer Collaborative Learning for Online Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel Peer Collaborative Learning method for online knowledge distillation, which integrates online ensembling and network collaboration into a unified framework. |
Guile Wu; Shaogang Gong; |
| 213 | Self-Supervised Attention-Aware Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we use visual attention as an inductive bias for RL agents. |
Haiping Wu; Khimya Khetarpal; Doina Precup; |
| 214 | Training Spiking Neural Networks with Accumulated Spiking Flow Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new backpropagation method for SNNs based on the accumulated spiking flow (ASF), i.e. ASF-BP. |
Hao Wu; Yueyi Zhang; Wenming Weng; Yongting Zhang; Zhiwei Xiong; Zheng-Jun Zha; Xiaoyan Sun; Feng Wu; |
| 215 | Fast and Scalable Adversarial Training of Kernel SVM Via Doubly Stochastic Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim at kernel SVM and propose adv-SVM to improve its adversarial robustness via adversarial training, which has been demonstrated to be the most promising defense techniques. |
Huimin Wu; Zhengmian Hu; Bin Gu; |
| 216 | Fine-grained Generalization Analysis of Vector-Valued Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. |
Liang Wu; Antoine Ledent; Yunwen Lei; Marius Kloft; |
| 217 | Frugal Optimization for Cost-related Hyperparameters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we develop a new cost-frugal HPO solution. |
Qingyun Wu; Chi Wang; Silu Huang; |
| 218 | Federated Block Coordinate Descent Scheme for Learning Global and Personalized Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we focus on two possible areas of improvement of the state of the art. |
Ruiyuan Wu; Anna Scaglione; Hoi-To Wai; Nurullah Karakoc; Kari Hreinsson; Wing-Kin Ma; |
| 219 | Curriculum-Meta Learning for Order-Robust Continual Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel curriculum-meta learning method to tackle the above two challenges in continual relation extraction. |
Tongtong Wu; Xuekai Li; Yuan-Fang Li; Gholamreza Haffari; Guilin Qi; Yujin Zhu; Guoqiang Xu; |
| 220 | Fractal Autoencoders for Feature Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). |
Xinxing Wu; Qiang Cheng; |
| 221 | Neural Architecture Search As Sparse Supernet Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. |
Yan Wu; Aoming Liu; Zhiwu Huang; Siwei Zhang; Luc Van Gool; |
| 222 | Learning to Purify Noisy Labels Via Meta Soft Label Corrector Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a meta-learning model, aiming at attaining an automatic scheme which can estimate soft labels through meta-gradient descent step under the guidance of a small amount of noise-free meta data. |
Yichen Wu; Jun Shu; Qi Xie; Qian Zhao; Deyu Meng; |
| 223 | Near-Optimal MNL Bandits Under Risk Criteria Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design algorithms for a broad class of risk criteria, including but not limited to the well-known conditional value-at-risk, Sharpe ratio, and entropy risk, and prove that they suffer a near-optimal regret. |
Guangyu Xi; Chao Tao; Yuan Zhou; |
| 224 | Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to fill the gap of decentralized quantized constrained optimization, we propose a novel communication-efficient Decentralized Quantized Stochastic Frank-Wolfe (DQSFW) algorithm for non-convex constrained learning models. |
Wenhan Xian; Feihu Huang; Heng Huang; |
| 225 | Physics-constrained Automatic Feature Engineering for Predictive Modeling in Materials Science Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we develop AFE to extract dependency relationships that can be interpreted with functional formulas to discover physics meaning or new hypotheses for the problems of interest. |
Ziyu Xiang; Mingzhou Fan; Guillermo Vázquez Tovar; William Trehern; Byung-Jun Yoon; Xiaofeng Qian; Raymundo Arroyave; Xiaoning Qian; |
| 226 | Distant Transfer Learning Via Deep Random Walk Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study distant transfer learning by proposing a DeEp Random Walk basEd distaNt Transfer (DERWENT) method. |
Qiao Xiao; Yu Zhang; |
| 227 | Learning Cycle-Consistent Cooperative Networks Via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the unsupervised cross-domain translation problem by proposing a generative framework, in which the probability distribution of each domain is represented by a generative cooperative network that consists of an energy-based model and a latent variable model. |
Jianwen Xie; Zilong Zheng; Xiaolin Fang; Song-Chun Zhu; Ying Nian Wu; |
| 228 | Learning Energy-Based Model with Variational Auto-Encoder As Amortized Sampler Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to learn a variational auto-encoder (VAE) to initialize the finite-step MCMC, such as Langevin dynamics that is derived from the energy function, for efficient amortized sampling of the EBM. |
Jianwen Xie; Zilong Zheng; Ping Li; |
| 229 | Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage. |
Jinwei Xing; Takashi Nagata; Kexin Chen; Xinyun Zou; Emre Neftci; Jeffrey L. Krichmar; |
| 230 | Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms Under Markovian Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our study develops new techniques for analyzing the Adam-type RL algorithms under Markovian sampling. |
Huaqing Xiong; Tengyu Xu; Yingbin Liang; Wei Zhang; |
| 231 | Variational Disentanglement for Rare Event Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: So motivated, we propose a variational disentanglement approach to semi-parametrically learn from rare events in heavily imbalanced classification problems. |
Zidi Xiu; Chenyang Tao; Michael Gao; Connor Davis; Benjamin A. Goldstein; Ricardo Henao; |
| 232 | Step-Ahead Error Feedback for Distributed Training with Compressed Gradient Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this critical problem, we propose two novel techniques, 1) step ahead and 2) error averaging, with rigorous theoretical analysis. |
An Xu; Zhouyuan Huo; Heng Huang; |
| 233 | Isolation Graph Kernel Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces an alternative called Isolation Graph Kernel (IGK) that measures the similarity between two attributed graphs. |
Bi-Cun Xu; Kai Ming Ting; Yuan Jiang; |
| 234 | Multi-Task Recurrent Modular Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose multi-task recurrent modular networks (MT-RMN) that can be incorporated in any multi-task recurrent models to address the above drawbacks. |
Dongkuan Xu; Wei Cheng; Xin Dong; Bo Zong; Wenchao Yu; Jingchao Ni; Dongjin Song; Xuchao Zhang; Haifeng Chen; Xiang Zhang; |
| 235 | Learning Graphons Via Structured Gromov-Wasserstein Barycenters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel and principled method to learn a nonparametric graph model called graphon, which is defined in an infinite-dimensional space and represents arbitrary-size graphs. |
Hongteng Xu; Dixin Luo; Lawrence Carin; Hongyuan Zha; |
| 236 | Towards Generalized Implementation of Wasserstein Distance in GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that the strong Lipschitz constraint might be unnecessary for optimization. |
Minkai Xu; |
| 237 | Towards Feature Space Adversarial Attack By Style Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new adversarial attack to Deep Neural Networks for image classification. |
Qiuling Xu; Guanhong Tao; Siyuan Cheng; Xiangyu Zhang; |
| 238 | MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend state-of-the-art neural architecture search (NAS) methods and propose MUltimodal Fusion Architecture SeArch (MUFASA) to simultaneously search across multimodal fusion strategies and modality-specific architectures for the first time. |
Zhen Xu; David R. So; Andrew M. Dai; |
| 239 | Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we utilize the Fourier analysis to empirically provide a promising mechanism to understand why feedforward deeper learning is faster. |
Zhiqin John Xu; Hanxu Zhou; |
| 240 | Rethinking Bi-Level Optimization in Neural Architecture Search: A Gibbs Sampling Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, one-shot neural architecture search is addressed by adopting a directed probabilistic graphical model to represent the joint probability distribution over data and model. |
Chao Xue; Xiaoxing Wang; Junchi Yan; Yonggang Hu; Xiaokang Yang; Kewei Sun; |
| 241 | Toward Understanding The Influence of Individual Clients in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we defined a new notion, called {\em Fed-Influence}, to quantify this influence over the model parameters, and proposed an effective and efficient algorithm to estimate this metric. |
Yihao Xue; Chaoyue Niu; Zhenzhe Zheng; Shaojie Tang; Chengfei Lyu; Fan Wu; Guihai Chen; |
| 242 | Adversarial Partial Multi-Label Learning with Label Disambiguation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel adversarial learning model, PML-GAN, under a generalized encoder-decoder framework for partial multi-label learning. |
Yan Yan; Yuhong Guo; |
| 243 | Near Lossless Transfer Learning for Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose CQ training (Clamped and Quantized training), an SNN-compatible CNN training algorithm with clamp and quantization that achieves near-zero conversion accuracy loss. |
Zhanglu Yan; Jun Zhou; Weng-Fai Wong; |
| 244 | DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning Via Adversarial Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel deep hidden backdoor (DeHiB) attack scheme for SSL-based systems. |
Zhicong Yan; Gaolei Li; Yuan TIan; Jun Wu; Shenghong Li; Mingzhe Chen; H. Vincent Poor; |
| 245 | Robust Bandit Learning with Imperfect Context Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study a novel contextual bandit setting in which only imperfect context is available for arm selection while the true context is revealed at the end of each round. |
Jianyi Yang; Shaolei Ren; |
| 246 | Hierarchical Graph Capsule Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. |
Jinyu Yang; Peilin Zhao; Yu Rong; Chaochao Yan; Chunyuan Li; Hehuan Ma; Junzhou Huang; |
| 247 | FracBits: Mixed Precision Quantization Via Fractional Bit-Widths Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel learning-based algorithm to derive mixed precision models end-to-end under target computation constraints and model sizes. |
Linjie Yang; Qing Jin; |
| 248 | On Convergence of Gradient Expected Sarsa(λ) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the convergence of Expected Sarsa(λ) with function approximation. |
Long Yang; Gang Zheng; Yu Zhang; Qian Zheng; Pengfei Li; Gang Pan; |
| 249 | Sample Complexity of Policy Gradient Finding Second-Order Stationary Points Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of FOSP, we consider SOSP as the convergence criteria to characterize the sample complexity of policy gradient. |
Long Yang; Qian Zheng; Gang Pan; |
| 250 | WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel reinforcement learning algorithm called Worst-Case Soft Actor Critic, which extends the Soft Actor Critic algorithm with a safety critic to achieve risk control. |
Qisong Yang; Thiago D. Simão; Simon H Tindemans; Matthijs T. J. Spaan; |
| 251 | Characterizing The Evasion Attackability of Multi-label Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Evasion attack in multi-label learning systems is an interesting, widely witnessed, yet rarely explored research topic. Characterizing the crucial factors determining the … |
Zhuo Yang; Yufei Han; Xiangliang Zhang; |
| 252 | SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. |
Ting Yao; Yiheng Zhang; Zhaofan Qiu; Yingwei Pan; Tao Mei; |
| 253 | ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we introduce ADAHESSIAN, a new stochastic optimization algorithm. |
Zhewei Yao; Amir Gholami; Sheng Shen; Mustafa Mustafa; Kurt Keutzer; Michael Mahoney; |
| 254 | Improving Sample Efficiency in Model-Free Reinforcement Learning from Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following these findings, we propose effective techniques to improve training stability. |
Denis Yarats; Amy Zhang; Ilya Kostrikov; Brandon Amos; Joelle Pineau; Rob Fergus; |
| 255 | Task Cooperation for Semi-Supervised Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the idea that unlabeled data can be utilized to smooth the model space in traditional semi-supervised learning, we propose TAsk COoperation (TACO) which takes advantage of unsupervised tasks to smooth the meta-model space. |
Han-Jia Ye; Xin-Chun Li; De-Chuan Zhan; |
| 256 | Amata: An Annealing Mechanism for Adversarial Training Acceleration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to reduce the computational cost, we propose an annealing mechanism, Amata, to reduce the overhead associated with adversarial training. |
Nanyang Ye; Qianxiao Li; Xiao-Yun Zhou; Zhanxing Zhu; |
| 257 | Sequential Generative Exploration Model for Partially Observable Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel reward shaping approach to infer the intrinsic rewards for the agent from a sequential generative model. |
Haiyan Yin; Jianda Chen; Sinno Jialin Pan; Sebastian Tschiatschek; |
| 258 | Enhanced Audio Tagging Via Multi- to Single-Modal Teacher-Student Mutual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the challenges, we present a novel visual-assisted teacher-student mutual learning framework for robust sound event detection from audio recordings. |
Yifang Yin; Harsh Shrivastava; Ying Zhang; Zhenguang Liu; Rajiv Ratn Shah; Roger Zimmermann; |
| 259 | Image-to-Image Retrieval By Learning Similarity Between Scene Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this idea, we propose a novel approach for image-to-image retrieval using scene graph similarity measured by graph neural networks. |
Sangwoong Yoon; Woo Young Kang; Sungwook Jeon; SeongEun Lee; Changjin Han; Jonghun Park; Eun-Sol Kim; |
| 260 | Learning Interpretable Models for Coupled Networks Under Domain Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the idea of coupled networks through an optimization framework by focusing on interactions between structural edges and functional edges of brain networks. |
Hongyuan You; Sikun Lin; Ambuj Singh; |
| 261 | Identity-aware Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. |
Jiaxuan You; Jonathan M Gomes-Selman; Rex Ying; Jure Leskovec; |
| 262 | How Does Data Augmentation Affect Privacy in Machine Learning? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish the optimal membership inference when the model is trained with augmented data, which inspires us to formulate the MI attack as a set classification problem, i.e., classifying a set of augmented instances instead of a single data point, and design input permutation invariant features. |
Da Yu; Huishuai Zhang; Wei Chen; Jian Yin; Tie-Yan Liu; |
| 263 | DAST: Unsupervised Domain Adaptation in Semantic Segmentation Based on Discriminator Attention and Self-Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we follow the trend to propose a novel method to reduce the domain shift using strategies of discriminator attention and self-training. |
Fei Yu; Mo Zhang; Hexin Dong; Sheng Hu; Bin Dong; Li Zhang; |
| 264 | Any-Precision Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. |
Haichao Yu; Haoxiang Li; Humphrey Shi; Thomas S. Huang; Gang Hua; |
| 265 | Personalized Adaptive Meta Learning for Cold-start User Preference Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: 2) To provide better personalized learning rates for each user, we introduce a similarity-based method to find similar users as a reference and a tree-based method to store users’ features for fast search. |
Runsheng Yu; Yu Gong; Xu He; Yu Zhu; Qingwen Liu; Wenwu Ou; Bo An; |
| 266 | Measuring Dependence with Matrix-based Entropy Functional Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we summarize and generalize the main idea of existing information-theoretic dependence measures into a higher-level perspective by the Shearer’s inequality. |
Shujian Yu; Francesco Alesiani; Xi Yu; Robert Jenssen; Jose Principe; |
| 267 | Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a la- bel generation module based on the self-supervised learning strategy to acquire independent unimodal supervisions. |
Wenmeng Yu; Hua Xu; Ziqi Yuan; Jiele Wu; |
| 268 | Knowledge-Guided Object Discovery with Acquired Deep Impressions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework called Acquired Deep Impressions (ADI) which continuously learns knowledge of objects as “impressions” for compositional scene understanding. |
Jinyang Yuan; Bin Li; Xiangyang Xue; |
| 269 | Curse or Redemption? How Data Heterogeneity Affects The Robustness of Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on characterizing and understanding its impact on backdooring attacks in federated learning through comprehensive experiments using synthetic and the LEAF benchmarks. |
Syed Zawad; Ahsan Ali; Pin-Yu Chen; Ali Anwar; Yi Zhou; Nathalie Baracaldo; Yuan Tian; Feng Yan; |
| 270 | Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness Under Non-uniform Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a weighted minimax risk optimization that defends against non-uniform attacks, achieving robustness against adversarial examples under perturbed test data distributions. |
Huimin Zeng; Chen Zhu; Tom Goldstein; Furong Huang; |
| 271 | Contrastive Self-supervised Learning for Graph Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose two approaches based on contrastive self-supervised learning (CSSL) to alleviate overfitting. |
Jiaqi Zeng; Pengtao Xie; |
| 272 | Data-driven Competitive Algorithms for Online Knapsack and Set Cover Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop an approach for data-driven design of online algorithms that maintain near-optimal worst-case guarantees while also performing learning in order to perform well for typical inputs. |
Ali Zeynali; Bo Sun; Mohammad Hajiesmaili; Adam Wierman; |
| 273 | A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel SG-MCMC algorithm, called Hybrid Stochastic Gradient Hamiltonian Monte Carlo (HSG-HMC) method, which needs merely one sample per iteration and possesses a simple structure with only one hyperparameter. |
Chao Zhang; Zhijian Li; Zebang Shen; Jiahao Xie; Hui Qian; |
| 274 | CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources. |
Chaoyun Zhang; Marco Fiore; Iain Murray; Paul Patras; |
| 275 | Exploration By Maximizing Renyi Entropy for Reward-Free RL Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the exploration phase, we propose to maximize the Renyi entropy over the state-action space and justify this objective theoretically. |
Chuheng Zhang; Yuanying Cai; Longbo Huang; Jian Li; |
| 276 | Efficient Folded Attention for Medical Image Reconstruction and Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a folded attention (FA) approach to improve the computational efficiency of traditional attention methods on 3D medical images. |
Hang Zhang; Jinwei Zhang; Rongguang Wang; Qihao Zhang; Pascal Spincemaille; Thanh D. Nguyen; Yi Wang; |
| 277 | Interpreting Multivariate Shapley Interactions in DNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN. |
Hao Zhang; Yichen Xie; Longjie Zheng; Die Zhang; Quanshi Zhang; |
| 278 | Sample Efficient Reinforcement Learning with REINFORCE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider classical policy gradient methods that compute an approximate gradient with a single trajectory or a fixed size mini-batch of trajectories under soft-max parametrization and log-barrier regularization, along with the widely-used REINFORCE gradient estimation procedure. |
Junzi Zhang; Jongho Kim; Brendan O’Donoghue; Stephen Boyd; |
| 279 | Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenging problems, we propose a novel VFL framework integrated with new backward updating mechanism and bilevel asynchronous parallel architecture (VFB^2), under which three new algorithms, including VFB^2-SGD, -SVRG, and -SAGA, are proposed. |
Qingsong Zhang; Bin Gu; Cheng Deng; Heng Huang; |
| 280 | Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. |
Shangtong Zhang; Bo Liu; Shimon Whiteson; |
| 281 | Deep Wasserstein Graph Discriminant Learning for Graph Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a deep Wasserstein graph discriminant learning (WGDL) framework to learn discriminative embeddings of graphs in Wasserstein-metric (W-metric) matching space. |
Tong Zhang; Yun Wang; Zhen Cui; Chuanwei Zhou; Baoliang Cui; Haikuan Huang; Jian Yang; |
| 282 | Treatment Effect Estimation with Disentangled Latent Factors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Much research has been devoted to the problem of estimating treatment effects from observational data; however, most methods assume that the observed variables only contain … |
Weijia Zhang; Lin Liu; Jiuyong Li; |
| 283 | Regret Bounds for Online Kernel Selection in Continuous Kernel Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to represent different learning frameworks of online kernel selection, we divide online kernel selection approaches in a continuous kernel space into two categories according to the order of selection and training at each round. |
Xiao Zhang; Shizhong Liao; Jun Xu; Ji-Rong Wen; |
| 284 | The Sample Complexity of Teaching By Reinforcement on Q-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on a specific family of reinforcement learning algorithms, Q-learning, and characterize the TDim under different teachers with varying control power over the environment, and present matching optimal teaching algorithms. |
Xuezhou Zhang; Shubham Bharti; Yuzhe Ma; Adish Singla; Xiaojin Zhu; |
| 285 | Partial-Label and Structure-constrained Deep Coupled Factorization Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we technically propose an enriched prior guided framework, called Dual-constrained Deep Semi-Supervised Coupled Factorization Network (DS2CF-Net), for discovering hierarchical coupled data representation. |
Yan Zhang; Zhao Zhang; Yang Wang; Zheng Zhang; Li Zhang; Shuicheng Yan; Meng Wang; |
| 286 | Memory-Gated Recurrent Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Because of the multivariate complexity in the evolution of the joint distribution that underlies the data generating process, we take a data-driven approach and construct a novel recurrent network architecture, termed Memory-Gated Recurrent Networks (mGRN), with gates explicitly regulating two distinct types of memories: the marginal memory and the joint memory. |
Yaquan Zhang; Qi Wu; Nanbo Peng; Min Dai; Jing Zhang; Hu Wang; |
| 287 | Towards Enabling Learnware to Handle Unseen Jobs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a novel scheme that works can effectively reuse the learnwares even when the user’s job involves unseen parts. |
Yu-Jie Zhang; Yu-Hu Yan; Peng Zhao; Zhi-Hua Zhou; |
| 288 | Exploiting Unlabeled Data Via Partial Label Assignment for Multi-Class Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, an intermediate unlabeled data exploitation strategy is investigated via partial label assignment, i.e. a set of candidate labels other than a single pseudo-label are assigned to the unlabeled data. |
Zhen-Ru Zhang; Qian-Wen Zhang; Yunbo Cao; Min-Ling Zhang; |
| 289 | Looking Wider for Better Adaptive Representation in Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these problems, we propose the Cross Non-Local Neural Network (CNL) for capturing the long-range dependency of the samples and the current task. |
Jiabao Zhao; Yifan Yang; Xin Lin; Jing Yang; Liang He; |
| 290 | Distilling Localization for Self-Supervised Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This is due to the fact that view generation process considers pixels in an image uniformly.To address this problem, we propose a data-driven approach for learning invariance to backgrounds. |
Nanxuan Zhao; Zhirong Wu; Rynson W.H. Lau; Stephen Lin; |
| 291 | Exploratory Machine Learning with Unknown Unknowns Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we point out that there is an important category of failure, which owes to the fact that there are unknown classes in the training data misperceived as other labels, and thus their existence was unknown from the given supervision. |
Peng Zhao; Yu-Jie Zhang; Zhi-Hua Zhou; |
| 292 | Efficient Classification with Adaptive KNN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an adaptive kNN method for classification, in which different k are selected for different test samples. |
Puning Zhao; Lifeng Lai; |
| 293 | Data Augmentation for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction. |
Tong Zhao; Yozen Liu; Leonardo Neves; Oliver Woodford; Meng Jiang; Neil Shah; |
| 294 | Augmenting Policy Learning with Routines Discovered from A Single Demonstration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose routine-augmented policy learning (RAPL), which discovers routines composed of primitive actions from a single demonstration and uses discovered routines to augment policy learning. |
Zelin Zhao; Chuang Gan; Jiajun Wu; Xiaoxiao Guo; Joshua B. Tenenbaum; |
| 295 | Improved Consistency Regularization for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We improve on this technique in several ways. |
Zhengli Zhao; Sameer Singh; Honglak Lee; Zizhao Zhang; Augustus Odena; Han Zhang; |
| 296 | Flow-based Generative Models for Learning Manifold to Manifold Mappings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: On the theoretical side, we introduce three kinds of invertible layers for manifold-valued data, which are not only analogous to their functionality in flow-based generative models (e.g., GLOW) but also preserve the key benefits (determinants of the Jacobian are easy to calculate). |
Xingjian Zhen; Rudrasis Chakraborty; Liu Yang; Vikas Singh; |
| 297 | Meta Label Correction for Noisy Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend this approach via posing the problem as a label correction problem within a meta-learning framework. |
Guoqing Zheng; Ahmed Hassan Awadallah; Susan Dumais; |
| 298 | Going Deeper With Directly-Trained Larger Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed “STBP-tdBN”, enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware. |
Hanle Zheng; Yujie Wu; Lei Deng; Yifan Hu; Guoqi Li; |
| 299 | Fully-Connected Tensor Network Decomposition and Its Application to Higher-Order Tensor Completion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generalized tensor decomposition, which decomposes an Nth-order tensor into a set of Nth-order factors and establishes an operation between any two factors. |
Yu-Bang Zheng; Ting-Zhu Huang; Xi-Le Zhao; Qibin Zhao; Tai-Xiang Jiang; |
| 300 | How Does The Combined Risk Affect The Performance of Unsupervised Domain Adaptation Approaches? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this key challenge, we propose a method named E-MixNet. |
Li Zhong; Zhen Fang; Feng Liu; Jie Lu; Bo Yuan; Guangquan Zhang; |
| 301 | Multi-task Learning By Leveraging The Semantic Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to leverage the label information in multi-task learning by exploring the semantic conditional relations among tasks. |
Fan Zhou; Brahim Chaib-draa; Boyu Wang; |
| 302 | MetaAugment: Sample-Aware Data Augmentation Policy Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we learn a sample-aware data augmentation policy efficiently by formulating it as a sample reweighting problem. |
Fengwei Zhou; Jiawei Li; Chuanlong Xie; Fei Chen; Lanqing Hong; Rui Sun; Zhenguo Li; |
| 303 | Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a ProbSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences’ dependency alignment. |
Haoyi Zhou; Shanghang Zhang; Jieqi Peng; Shuai Zhang; Jianxin Li; Hui Xiong; Wancai Zhang; |
| 304 | Inverse Reinforcement Learning with Natural Language Goals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel adversarial inverse reinforcement learning algorithm to learn a language-conditioned policy and reward function. |
Li Zhou; Kevin Small; |
| 305 | Tri-level Robust Clustering Ensemble with Multiple Graph Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to address this problem, we propose a novel Tri-level Robust Clustering Ensemble (TRCE) method by transforming the clustering ensemble problem to a multiple graph learning problem. |
Peng Zhou; Liang Du; Yi-Dong Shen; Xuejun Li; |
| 306 | Fairness in Forecasting and Learning Linear Dynamical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce two natural notions of subgroup fairness and instantaneous fairness to address such under-representation bias in time-series forecasting problems. |
Quan Zhou; Jakub Marecek; Robert N. Shorten; |
| 307 | Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop an energy-efficient phase-domain signal processing circuit for the neuron and propose a direct-train deep SNN framework. |
Shibo Zhou; Xiaohua Li; Ying Chen; Sanjeev T. Chandrasekaran; Arindam Sanyal; |
| 308 | Local Differential Privacy for Bayesian Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the increasing concern about privacy in nowadays data-intensive online learning systems, we consider a black-box optimization in the nonparametric Gaussian process setting with local differential privacy (LDP) guarantee. |
Xingyu Zhou; Jian Tan; |
| 309 | A Primal-Dual Online Algorithm for Online Matching Problem in Dynamic Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the online matching problem in dynamic environments in which the dual optimal prices are allowed to vary over time. |
Yu-Hang Zhou; Peng Hu; Chen Liang; Huan Xu; Guangda Huzhang; Yinfu Feng; Qing Da; Xinshang Wang; An-Xiang Zeng; |
| 310 | Graph Neural Networks with Heterophily Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily. |
Jiong Zhu; Ryan A. Rossi; Anup Rao; Tung Mai; Nedim Lipka; Nesreen K. Ahmed; Danai Koutra; |
| 311 | Bias and Variance of Post-processing in Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper takes a first step towards understanding the properties of post-processing. |
Keyu Zhu; Pascal Van Hentenryck; Ferdinando Fioretto; |
| 312 | Self-correcting Q-learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. |
Rong Zhu; Mattia Rigotti; |
| 313 | An Efficient Algorithm for Deep Stochastic Contextual Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formulate the SCB that uses a DNN reward function as a non-convex stochastic optimization problem, and design a stage-wised stochastic gradient descent algorithm to optimize the problem and determine the action policy. |
Tan Zhu; Guannan Liang; Chunjiang Zhu; Haining Li; Jinbo Bi; |
| 314 | Variational Fair Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general variational framework of fair clustering, which integrates an original Kullback-Leibler (KL) fairness term with a large class of clustering objectives, including prototype or graph based. |
Imtiaz Masud Ziko; Jing Yuan; Eric Granger; Ismail Ben Ayed; |
| 315 | Learning Task-Distribution Reward Shaping with Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide insights into optimal reward shaping, and propose a novel meta-learning framework to automatically learn such reward shaping to apply on newly sampled tasks. |
Haosheng Zou; Tongzheng Ren; Dong Yan; Hang Su; Jun Zhu; |
| 316 | Improving Continuous-time Conflict Based Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we begin to close this gap and explore how to adapt successful CBS improvements, namely, prioritizing conflicts (PC), disjoint splitting (DS), and high-level heuristics, to the continuous time setting of CCBS. |
Anton Andreychuk; Konstantin Yakovlev; Eli Boyarski; Roni Stern; |
| 317 | Inference-Based Deterministic Messaging For Multi-Agent Communication Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human … |
Varun Bhatt; Michael Buro; |
| 318 | Scalable and Safe Multi-Agent Motion Planning with Nonlinear Dynamics and Bounded Disturbances Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a scalable and effective multi-agent safe motion planner that enables a group of agents to move to their desired locations while avoiding collisions with obstacles and other agents, with the presence of rich obstacles, high-dimensional, nonlinear, nonholonomic dynamics, actuation limits, and disturbances. |
Jingkai Chen; Jiaoyang Li; Chuchu Fan; Brian C. Williams; |
| 319 | Learning to Resolve Conflicts for Multi-Agent Path Finding with Conflict-Based Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose a machine-learning (ML) framework for conflict selection that observes the decisions made by the oracle and learns a conflict-selection strategy represented by a linear ranking function that imitates the oracle’s decisions accurately and quickly. |
Taoan Huang; Sven Koenig; Bistra Dilkina; |
| 320 | The Influence of Memory in Multi-Agent Consensus Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a framework to study what we call `memory consensus protocol’. |
David Kohan Marzagão; Luciana Basualdo Bonatto; Tiago Madeira; Marcelo Matheus Gauy; Peter McBurney; |
| 321 | Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make progress in this direction, we study a smooth analogue of Q-learning. |
Stefanos Leonardos; Georgios Piliouras; |
| 322 | Lifelong Multi-Agent Path Finding in Large-Scale Warehouses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the lifelong variant of MAPF, where agents are constantly engaged with new goal locations, such as in large-scale automated warehouses. |
Jiaoyang Li; Andrew Tinka; Scott Kiesel; Joseph W. Durham; T. K. Satish Kumar; Sven Koenig; |
| 323 | Dec-SGTS: Decentralized Sub-Goal Tree Search for Multi-Agent Coordination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a novel multi-agent coordination protocol based on subgoal intentions, defined as the probability distribution over feasible subgoal sequences. |
Minglong Li; Zhongxuan Cai; Wenjing Yang; Lixia Wu; Yinghui Xu; Ji Wang; |
| 324 | Expected Value of Communication for Planning in Ad Hoc Teamwork Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the scenario in which teammates can communicate with one another, but only at a cost. |
William Macke; Reuth Mirsky; Peter Stone; |
| 325 | Time-Independent Planning for Multiple Moving Agents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an alternative approach, called time-independent planning, which is both online and distributed. |
Keisuke Okumura; Yasumasa Tamura; Xavier Défago; |
| 326 | Resilient Multi-Agent Reinforcement Learning with Adversarial Value Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose Resilient Adversarial value Decomposition with Antagonist-Ratios (RADAR). |
Thomy Phan; Lenz Belzner; Thomas Gabor; Andreas Sedlmeier; Fabian Ritz; Claudia Linnhoff-Popien; |
| 327 | Anytime Heuristic and Monte Carlo Methods for Large-Scale Simultaneous Coalition Structure Generation and Assignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In light of this, and to make it possible to generate better feasible solutions for difficult large-scale problems efficiently, we present and benchmark several different anytime algorithms that use general-purpose heuristics and Monte Carlo techniques to guide search. |
Fredrik Präntare; Herman Appelgren; Fredrik Heintz; |
| 328 | Newton Optimization on Helmholtz Decomposition for Continuous Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose NOHD (Newton Optimization on Helmholtz Decomposition), a Newton-like algorithm for multi-agent learning problems based on the decomposition of the dynamics of the system in its irrotational (Potential) and solenoidal (Hamiltonian) component. |
Giorgia Ramponi; Marcello Restelli; |
| 329 | Synchronous Dynamical Systems on Directed Acyclic Graphs: Complexity and Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that computational intractability results for reachability problems hold even for dynamical systems on directed acyclic graphs (dags). |
Daniel J. Rosenkrantz; Madhav Marathe; S. S. Ravi; Richard E. Stearns; |
| 330 | Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we move away from the artificial divide between dynamic agents and static games, to introduce and analyze a large class of competitive settings where both the agents and the games they play evolve strategically over time. |
Stratis Skoulakis; Tanner Fiez; Ryann Sim; Georgios Piliouras; Lillian Ratliff; |
| 331 | Value-Decomposition Multi-Agent Actor-Critics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decomposition to actor-critic methods that are compatible with A2C and propose a novel actor-critic framework, value-decomposition actor-critic (VDAC). |
Jianyu Su; Stephen Adams; Peter Beling; |
| 332 | Contract-based Inter-user Usage Coordination in Free-floating Car Sharing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel distributed user-car matching method based on a contract between users to mitigate the imbalance problem between vehicle distribution and demand in free-floating car sharing. |
Kentaro Takahira; Shigeo Matsubara; |
| 333 | Maintenance of Social Commitments in Multiagent Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce and formalize a concept of a maintenance commitment, a kind of social commitment characterized by states whose truthhood an agent commits to maintain. |
Pankaj Telang; Munindar P. Singh; Neil Yorke-Smith; |
| 334 | Efficient Querying for Cooperative Probabilistic Commitments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a solution to the problem of how cooperative agents can efficiently find an (approximately) optimal commitment by querying about carefully-selected commitment choices. |
Qi Zhang; Edmund H. Durfee; Satinder Singh; |
| 335 | Coordination Between Individual Agents in Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, in this paper we propose an agent-level coordination based MARL method. |
Yang Zhang; Qingyu Yang; Dou An; Chengwei Zhang; |
| 336 | Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. |
Seojin Bang; Pengtao Xie; Heewook Lee; Wei Wu; Eric Xing; |
| 337 | Is The Most Accurate AI The Best Teammate? Optimizing AI for Teamwork Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We discuss the shortcoming of current optimization approaches beyond well-studied loss functions such as log-loss, and encourage future work on AI optimization problems motivated by human-AI collaboration. |
Gagan Bansal; Besmira Nushi; Ece Kamar; Eric Horvitz; Daniel S. Weld; |
| 338 | TripleTree: A Versatile Interpretable Representation of Black Box Agents and Their Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We create such a representation using a novel variant of the CART decision tree algorithm, and demonstrate how it facilitates practical understanding of black box agents through prediction, visualisation and rule-based explanation. |
Tom Bewley; Jonathan Lawry; |
| 339 | Bayes-TrEx: A Bayesian Sampling Approach to Model Transparency By Example Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx. |
Serena Booth; Yilun Zhou; Ankit Shah; Julie Shah; |
| 340 | FIMAP: Feature Importance By Minimal Adversarial Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Feature Importance by Minimal Adversarial Perturbation (FIMAP), a neural network based approach that unifies feature importance and counterfactual explanations. |
Matt Chapman-Rounds; Umang Bhatt; Erik Pazos; Marc-Andre Schulz; Konstantinos Georgatzis; |
| 341 | Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption.The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN). |
Pengfei Chen; Junjie Ye; Guangyong Chen; Jingwei Zhao; Pheng-Ann Heng; |
| 342 | Robustness of Accuracy Metric and Its Inspirations in Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We concretize this finding’s inspiration in two essential aspects: training and validation, with which we address critical issues in learning with noisy labels. |
Pengfei Chen; Junjie Ye; Guangyong Chen; Jingwei Zhao; Pheng-Ann Heng; |
| 343 | A Unified Taylor Framework for Revisiting Attribution Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge the gap, in this paper, we propose a Taylor attribution framework and reformulate seven mainstream attribution methods into the framework. |
Huiqi Deng; Na Zou; Mengnan Du; Weifu Chen; Guocan Feng; Xia Hu; |
| 344 | Verifiable Machine Ethics in Changing Contexts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the use of a reasoning cycle, in which information about the ethical reasoner’s context is imported in a logical form, and we propose that context-specific aspects of an ethical encoding be prefaced by a guard formula. |
Louise A. Dennis; Martin Mose Bentzen; Felix Lindner; Michael Fisher; |
| 345 | Epistemic Logic of Know-Who Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper suggests a definition of "know who" as a modality using Grove-Halpern semantics of names. |
Sophia Epstein; Pavel Naumov; |
| 346 | Agent Incentives: A Causal Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework for analysing agent incentives using causal influence diagrams. |
Tom Everitt; Ryan Carey; Eric D. Langlois; Pedro A. Ortega; Shane Legg; |
| 347 | Individual Fairness in Kidney Exchange Programs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, the existence of multiple optimal plans for a KEP is explored as a mean to achieve individual fairness. |
Golnoosh Farnadi; William St-Arnaud; Behrouz Babaki; Margarida Carvalho; |
| 348 | Fair Representations By Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel unsupervised approach to map data into a compressed binary representation independent of sensitive attributes. |
Xavier Gitiaux; Huzefa Rangwala; |
| 349 | Amnesiac Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present two efficient methods that address this question of how a model owner or data holder may delete personal data from models in such a way that they may not be vulnerable to model inversion and membership inference attacks while maintaining model efficacy. |
Laura Graves; Vineel Nagisetty; Vijay Ganesh; |
| 350 | On The Verification of Neural ODEs with Stochastic Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this purpose, we introduce Stochastic Lagrangian Reachability (SLR), an abstraction-based technique for constructing a tight Reachtube (an over-approximation of the set of reachable states over a given time-horizon), and provide stochastic guarantees in the form of confidence intervals for the Reachtube bounds. |
Sophie Grunbacher; Ramin Hasani; Mathias Lechner; Jacek Cyranka; Scott A. Smolka; Radu Grosu; |
| 351 | PenDer: Incorporating Shape Constraints Via Penalized Derivatives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We notice that many such common shapes are related to derivatives, and propose a new approach, PenDer (Penalizing Derivatives), which incorporates these shape constraints by penalizing the derivatives. |
Akhil Gupta; Lavanya Marla; Ruoyu Sun; Naman Shukla; Arinbjörn Kolbeinsson; |
| 352 | Visualization of Supervised and Self-Supervised Neural Networks Via Attribution Guided Factorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we integrate two lines of research: gradient-based methods and attribution-based methods, and develop an algorithm that provides per-class explainability. |
Shir Gur; Ameen Ali; Lior Wolf; |
| 353 | Differentially Private Clustering Via Maximum Coverage Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present polynomial algorithms with constant multiplicative error and lower additive error than the previous state-of-the-art for each problem. |
Matthew Jones; Huy L. Nguyen; Thy D Nguyen; |
| 354 | Ordered Counterfactual Explanation By Mixed-Integer Linear Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this purpose, we propose a new framework called Ordered Counterfactual Explanation (OrdCE). |
Kentaro Kanamori; Takuya Takagi; Ken Kobayashi; Yuichi Ike; Kento Uemura; Hiroki Arimura; |
| 355 | On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper advances a novel method for generating plausible counterfactuals and semi-factuals for black-box CNN classifiers doing computer vision. |
Eoin M. Kenny; Mark T Keane; |
| 356 | How RL Agents Behave When Their Actions Are Modified Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the Modified-Action Markov Decision Process, an extension of the MDP model that allows actions to differ from the policy. |
Eric D. Langlois; Tom Everitt; |
| 357 | Outlier Impact Characterization for Time Series Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, for the first time, we study the characteristics of such outliers through the lens of the influence functional from robust statistics. |
Jianbo Li; Lecheng Zheng; Yada Zhu; Jingrui He; |
| 358 | Interpreting Deep Neural Networks with Relative Sectional Propagation By Analyzing Comparative Gradients and Hostile Activations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new attribution method, Relative Sectional Propagation (RSP), for fully decomposing the output predictions with the characteristics of class-discriminative attributions and clear objectness. |
Woo-Jeoung Nam; Jaesik Choi; Seong-Whan Lee; |
| 359 | Ethical Dilemmas in Strategic Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes to capture ethical dilemmas as a modality in strategic game settings with and without limit on sacrifice and for perfect and imperfect information games. |
Pavel Naumov; Rui-Jie Yew; |
| 360 | Comprehension and Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper suggests to interpret comprehension as a modality and proposes a complete bimodal logical system that describes an interplay between comprehension and knowledge modalities. |
Pavel Naumov; Kevin Ros; |
| 361 | Fair Influence Maximization: A Welfare Optimization Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we propose a framework based on social welfare theory, wherein the cardinal utilities derived by each community are aggregated using the isoelastic social welfare functions. |
Aida Rahmattalabi; Shahin Jabbari; Himabindu Lakkaraju; Phebe Vayanos; Max Izenberg; Ryan Brown; Eric Rice; Milind Tambe; |
| 362 | Explaining Convolutional Neural Networks Through Attribution-Based Input Sampling and Block-Wise Feature Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique and aggregate them to reach a fine-grained and complete explanation. |
Sam Sattarzadeh; Mahesh Sudhakar; Anthony Lem; Shervin Mehryar; Konstantinos N Plataniotis; Jongseong Jang; Hyunwoo Kim; Yeonjeong Jeong; Sangmin Lee; Kyunghoon Bae; |
| 363 | Exploring The Vulnerability of Deep Neural Networks: A Study of Parameter Corruption Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an indicator to measure the robustness of neural network parameters by exploiting their vulnerability via parameter corruption. |
Xu Sun; Zhiyuan Zhang; Xuancheng Ren; Ruixuan Luo; Liangyou Li; |
| 364 | Ethically Compliant Sequential Decision Making Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel approach for building ethically compliant autonomous systems that optimize completing a task while following an ethical framework. |
Justin Svegliato; Samer B. Nashed; Shlomo Zilberstein; |
| 365 | Improving Robustness to Model Inversion Attacks Via Mutual Information Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Mutual Information Regularization based Defense (MID) against MI attacks. |
Tianhao Wang; Yuheng Zhang; Ruoxi Jia; |
| 366 | Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a tighter linear approximation approach for the robustness verification of Convolutional Neural Networks (CNNs). |
Yiting Wu; Min Zhang; |
| 367 | Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we rethink the ACE algorithm of Ghorbani et~al., proposing an alternative invertible concept-based explanation (ICE) framework to overcome its shortcomings. |
Ruihan Zhang; Prashan Madumal; Tim Miller; Krista A. Ehinger; Benjamin I. P. Rubinstein; |
| 368 | I-Algebra: Towards Interactive Interpretability of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that DNN interpretability should be implemented as the interactions between users and models. |
Xinyang Zhang; Ren Pang; Shouling Ji; Fenglong Ma; Ting Wang; |
| 369 | Decision-Guided Weighted Automata Extraction from Recurrent Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. |
Xiyue Zhang; Xiaoning Du; Xiaofei Xie; Lei Ma; Yang Liu; Meng Sun; |
| 370 | Computing Plan-Length Bounds Using Lengths of Longest Paths Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We devise a method to exactly compute the length of the longest simple path in factored state spaces, like state spaces encountered in classical planning. |
Mohammad Abdulaziz; Dominik Berger; |
| 371 | Constrained Risk-Averse Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Under the assumption that the risk objectives and constraints can be represented by a Markov risk transition mapping, we propose an optimization-based method to synthesize Markovian policies that lower-bound the constrained risk-averse problem. |
Mohamadreza Ahmadi; Ugo Rosolia; Michel D. Ingham; Richard M. Murray; Aaron D. Ames; |
| 372 | Contract Scheduling With Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the setting in which there is a potentially erroneous prediction concerning the interruption. |
Spyros Angelopoulos; Shahin Kamali; |
| 373 | Responsibility Attribution in Parameterized Markovian Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of responsibility attribution in the setting of parametric Markov chains. |
Christel Baier; Florian Funke; Rupak Majumdar; |
| 374 | Symbolic Search for Optimal Total-Order HTN Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel approach to optimal (totally-ordered) HTN planning, which is based on symbolic search. |
Gregor Behnke; David Speck; |
| 375 | A Multivariate Complexity Analysis of The Material Consumption Scheduling Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Roughly speaking, the problem deals with minimizing the makespan when scheduling jobs that consume non-renewable resources. |
Matthias Bentert; Robert Bredereck; Péter Györgyi; Andrzej Kaczmarczyk; Rolf Niedermeier; |
| 376 | General Policies, Representations, and Planning Width Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this question by relating bounded width and serialized width to ideas of generalized planning, where general policies aim to solve multiple instances of a planning problem all at once. |
Blai Bonet; Hector Geffner; |
| 377 | Successor Feature Sets: Generalizing Successor Representations Across Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we bring together ideas from predictive state representations, belief space value iteration, successor features, and convex analysis: we develop a new, general successor-style representation, together with a Bellman equation that connects multiple sources of information within this representation, including different latent states, policies, and reward functions. |
Kianté Brantley; Soroush Mehri; Geoff J. Gordon; |
| 378 | GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning Via Goal-Literal Babbling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by human curiosity, we propose goal-literal babbling (GLIB), a simple and general method for exploration in such problems. |
Rohan Chitnis; Tom Silver; Joshua B. Tenenbaum; Leslie Pack Kaelbling; Tomás Lozano-Pérez; |
| 379 | Robust Finite-State Controllers for Uncertain POMDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop an algorithm to compute finite-memory policies for uPOMDPs that robustly satisfy specifications against any admissible distribution. |
Murat Cubuktepe; Nils Jansen; Sebastian Junges; Ahmadreza Marandi; Marnix Suilen; Ufuk Topcu; |
| 380 | Learning General Planning Policies from Small Examples Without Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce an alternative approach for computing more expressive general policies which does not require sample plans or a QNP planner. |
Guillem Francès; Blai Bonet; Hector Geffner; |
| 381 | Revisiting Dominance Pruning in Decoupled Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is a stronger variant of dominance checking for optimal planning, where efficiency and pruning power are most crucial. |
Daniel Gnad; |
| 382 | Equitable Scheduling on A Single Machine Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a natural but seemingly yet unstudied generalization of the problem of scheduling jobs on a single machine so as to minimize the number of tardy jobs. |
Klaus Heeger; Dan Hermelin; George B. Mertzios; Hendrik Molter; Rolf Niedermeier; Dvir Shabtay; |
| 383 | Landmark Generation in HTN Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel LM generation method for Hierarchical Task Network (HTN) planning and show that it is sound and incomplete. |
Daniel Höller; Pascal Bercher; |
| 384 | Endomorphisms of Classical Planning Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we employ structure-preserving maps on labeled transition systems (LTSs), namely endomorphisms well known from model theory, in order to detect redundancy. |
Rostislav Horčík; Daniel Fišer; |
| 385 | Bike-Repositioning Using Volunteers: Crowd Sourcing with Choice Restriction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method that can be used to deploy the volunteers in the system, based on the real time distribution of the bikes in different stations. |
Jinjia Huang; Mabel C. Chou; Chung-Piaw Teo; |
| 386 | Branch and Price for Bus Driver Scheduling with Complex Break Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a Branch and Price approach for a real-life Bus Driver Scheduling problem with a complex set of break constraints. |
Lucas Kletzander; Nysret Musliu; Pascal Van Hentenryck; |
| 387 | On-line Learning of Planning Domains from Sensor Data in PAL: Scaling Up to Large State Spaces Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach to learn an extensional representation of a discrete deterministic planning domain from observations in a continuous space navigated by the agent actions. |
Leonardo Lamanna; Alfonso Emilio Gerevini; Alessandro Saetti; Luciano Serafini; Paolo Traverso; |
| 388 | Progression Heuristics for Planning with Probabilistic LTL Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present novel admissible heuristics to guide the search for cost-optimal policies for these problems. |
Ian Mallett; Sylvie Thiebaux; Felipe Trevizan; |
| 389 | Bayesian Optimized Monte Carlo Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a general method for efficient action sampling based on Bayesian optimization. |
John Mern; Anil Yildiz; Zachary Sunberg; Tapan Mukerji; Mykel J. Kochenderfer; |
| 390 | Improved POMDP Tree Search Planning with Prioritized Action Branching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. |
John Mern; Anil Yildiz; Lawrence Bush; Tapan Mukerji; Mykel J. Kochenderfer; |
| 391 | Synthesis of Search Heuristics for Temporal Planning Via Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim at exploiting recent advances in reinforcement learning, for the synthesis of heuristics for temporal planning. |
Andrea Micheli; Alessandro Valentini; |
| 392 | Revealing Hidden Preconditions and Effects of Compound HTN Planning Tasks – A Complexity Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As relevant special case we introduce a problem relaxation which admits reasoning about preconditions and effects in polynomial time. |
Conny Olz; Susanne Biundo; Pascal Bercher; |
| 393 | Faster and Better Simple Temporal Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we give a structural characterization and extend the tractability frontier of the Simple Temporal Problem (STP) by defining the class of the Extended Simple Temporal Problem (ESTP), which augments STP with strict inequalities and monotone Boolean formulae on inequations (i.e., formulae involving the operations of conjunction, disjunction and parenthesization). |
Dario Ostuni; Alice Raffaele; Romeo Rizzi; Matteo Zavatteri; |
| 394 | Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel method named Generalizable Independent Latent Excitation (GILE) for human activity recognition, which greatly enhances the cross-person generalization capability of the model. |
Hangwei Qian; Sinno Jialin Pan; Chunyan Miao; |
| 395 | Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. |
Marc Rigter; Bruno Lacerda; Nick Hawes; |
| 396 | An LP-Based Approach for Goal Recognition As Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a method based on the operator-counting framework that efficiently computes solutions that satisfy the observations and uses the information generated to solve goal recognition tasks. |
Luísa R. A. Santos; Felipe Meneguzzi; Ramon Fraga Pereira; André Grahl Pereira; |
| 397 | Saturated Post-hoc Optimization for Classical Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show how to apply this idea to post-hoc optimization and obtain a heuristic that dominates the original both in theory and on the IPC benchmarks. |
Jendrik Seipp; Thomas Keller; Malte Helmert; |
| 398 | Improved Knowledge Modeling and Its Use for Signaling in Multi-Agent Planning with Partial Observability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe a planner that uses richer information about agents’ knowledge to improve upon QDec-FP. |
Shashank Shekhar; Ronen I. Brafman; Guy Shani; |
| 399 | Planning with Learned Object Importance in Large Problem Instances Using Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this challenge by learning to predict a small set of objects that, taken together, would be sufficient for finding a plan. |
Tom Silver; Rohan Chitnis; Aidan Curtis; Joshua B. Tenenbaum; Tomás Lozano-Pérez; Leslie Pack Kaelbling; |
| 400 | Symbolic Search for Oversubscription Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the use of symbolic search for optimal oversubscription planning. |
David Speck; Michael Katz; |
| 401 | Online Action Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we introduce the problem of Online Action Recognition. |
Alejandro Suárez-Hernández; Javier Segovia-Aguas; Carme Torras; Guillem Alenyà; |
| 402 | A Complexity-theoretic Analysis of Green Pickup-and-Delivery Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Nevertheless, we demonstrate in this paper an inherent intractability of these green components themselves. |
Xing Tan; Jimmy Xiangji Huang; |
| 403 | Faster Stackelberg Planning Via Symbolic Search and Information Sharing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we introduce new methods to tackle this source of complexity, through sharing information across follower tasks. |
Álvaro Torralba; Patrick Speicher; Robert Künnemann; Marcel Steinmetz; Jörg Hoffmann; |
| 404 | On The Optimal Efficiency of A* with Dominance Pruning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend this analysis for A* with dominance pruning, which exploits a dominance relation to eliminate some nodes during the search. |
Álvaro Torralba; |
| 405 | Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we mitigate this by representing objectives as automata in order to define novel reward shaping functions over this structured representation. |
Alvaro Velasquez; Brett Bissey; Lior Barak; Andre Beckus; Ismail Alkhouri; Daniel Melcer; George Atia; |
| 406 | Asking The Right Questions: Learning Interpretable Action Models Through Query Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contributions are a new paradigm for estimating such models using a rudimentary query interface with the agent and a hierarchical querying algorithm that generates an interrogation policy for estimating the agent’s internal model in a user-interpretable vocabulary. |
Pulkit Verma; Shashank Rao Marpally; Siddharth Srivastava; |
| 407 | Competitive Analysis for Two-Level Ski-Rental Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study a two-level ski-rental problem. |
Binghan Wu; Wei Bao; Dong Yuan; |
| 408 | Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems. |
Liang Xin; Wen Song; Zhiguang Cao; Jie Zhang; |
| 409 | Group Fairness By Probabilistic Modeling with Latent Fair Decisions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to closely model the data distribution, we employ probabilistic circuits, an expressive and tractable probabilistic model, and propose an algorithm to learn them from incomplete data. |
YooJung Choi; Meihua Dang; Guy Van den Broeck; |
| 410 | GO Hessian for Expectation-Based Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the GO gradient, we present for E_q_γ(y) [f(y)] an unbiased low-variance Hessian estimator, named GO Hessian, which contains the deterministic Hessian as a special case. |
Yulai Cong; Miaoyun Zhao; Jianqiao Li; Junya Chen; Lawrence Carin; |
| 411 | Better Bounds on The Adaptivity Gap of Influence Maximization Under Full-adoption Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To prove our bounds, we introduce new techniques to relate adaptive policies with non-adaptive ones that might be of their own interest. |
Gianlorenzo D’Angelo; Debashmita Poddar; Cosimo Vinci; |
| 412 | Uncertainty Quantification in CNN Through The Bootstrap of Convex Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel bootstrap based framework for the estimation of prediction uncertainty. |
Hongfei Du; Emre Barut; Fang Jin; |
| 413 | Scalable First-Order Methods for Robust MDPs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes the first first-order framework for solving robust MDPs. |
Julien Grand-Clément; Christian Kroer; |
| 414 | High Dimensional Level Set Estimation with Bayesian Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes novel methods to solve the high dimensional LSE problems using Bayesian Neural Networks. |
Huong Ha; Sunil Gupta; Santu Rana; Svetha Venkatesh; |
| 415 | A Generative Adversarial Framework for Bounding Confounded Causal Effects Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a bounding method for estimating the average causal effect (ACE) under unidentifiable situations due to hidden confounding based on Pearl’s structural causal model. |
Yaowei Hu; Yongkai Wu; Lu Zhang; Xintao Wu; |
| 416 | Estimating Identifiable Causal Effects Through Double Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new, general class of estimators for any identifiable causal functionals that exhibit DML properties, which we name DML-ID. |
Yonghan Jung; Jin Tian; Elias Bareinboim; |
| 417 | Relational Boosted Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Relational Boosted Bandits (RB2), a contextual bandits algorithm for relational domains based on (relational) boosted trees. |
Ashutosh Kakadiya; Sriraam Natarajan; Balaraman Ravindran; |
| 418 | Instrumental Variable-based Identification for Causal Effects Using Covariate Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from existing studies, we propose novel identification conditions of joint probabilities of potential outcomes, which allow us to derive a consistent estimator of the causal effect. |
Yuta Kawakami; |
| 419 | Learning Continuous High-Dimensional Models Using Mutual Information and Copula Bayesian Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new framework to learn non-parametric graphical models from continuous observational data. |
Marvin Lasserre; Régis Lebrun; Pierre-Henri Wuillemin; |
| 420 | Submodel Decomposition Bounds for Influence Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a model decomposition framework in both IDs and LIMIDs, which we call submodel decomposition that generates a tree of single-stage decision problems through a tree clustering scheme. |
Junkyu Lee; Radu Marinescu; Rina Dechter; |
| 421 | A New Bounding Scheme for Influence Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new bounding scheme for MEU that applies partitioning based approximations on top of the decomposition scheme called a multi-operator cluster DAG for influence diagrams that is more sensitive to the underlying structure of the model than the classical join-tree decomposition of influence diagrams. |
Radu Marinescu; Junkyu Lee; Rina Dechter; |
| 422 | Estimation of Spectral Risk Measures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of estimating a spectral risk measure (SRM) from i.i.d. samples, and propose a novel method that is based on numerical integration. |
Ajay Kumar Pandey; Prashanth L.A.; Sanjay P. Bhat; |
| 423 | Probabilistic Dependency Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Probabilistic Dependency Graphs (PDGs), a new class of directed graphical models. |
Oliver Richardson; Joseph Y Halpern; |
| 424 | Robust Contextual Bandits Via Bootstrapping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To demonstrate the versatility of the estimator, we apply it to design a BootLinUCB algorithm for the contextual bandit. |
Qiao Tang; Hong Xie; Yunni Xia; Jia Lee; Qingsheng Zhu; |
| 425 | Learning The Parameters of Bayesian Networks from Uncertain Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach for learning Bayesian network parameters that explicitly incorporates such uncertainty, and which is a natural extension of the Bayesian network formalism. |
Segev Wasserkrug; Radu Marinescu; Sergey Zeltyn; Evgeny Shindin; Yishai A Feldman; |
| 426 | Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that these tasks can be performed in polynomial time, solving a long-standing open problem in this area. |
Marcel Wienöbst; Max Bannach; Maciej Liskiewicz; |
| 427 | Bounding Causal Effects on Continuous Outcome Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present novel non-parametric methods to bound causal effects on the continuous outcome from studies with imperfect compliance. |
Junzhe Zhang; Elias Bareinboim; |
| 428 | A Fast Exact Algorithm for The Resource Constrained Shortest Path Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces several heuristics in the resource constrained path finding context that significantly improve the algorithmic performance of the initialisation phase and the core search. |
Saman Ahmadi; Guido Tack; Daniel D. Harabor; Philip Kilby; |
| 429 | Generalization in Portfolio-Based Algorithm Selection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the first provable guarantees for portfolio-based algorithm selection. |
Maria-Florina Balcan; Tuomas Sandholm; Ellen Vitercik; |
| 430 | Combining Preference Elicitation with Local Search and Greedy Search for Matroid Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two incremental preference elicitation methods for interactive preference-based optimization on weighted matroid structures. |
Nawal Benabbou; Cassandre Leroy; Thibaut Lust; Patrice Perny; |
| 431 | F-Aware Conflict Prioritization & Improved Heuristics For Conflict-Based Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we introduce an expanded categorization of conflicts, which first resolves conflicts where the f-values of the child nodes are larger than the f-value of the node to be split, and present a method for identifying such conflicts. |
Eli Boyarski; Ariel Felner; Pierre Le Bodic; Daniel D. Harabor; Peter J. Stuckey; Sven Koenig; |
| 432 | Parameterized Algorithms for MILPs with Small Treedepth Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend this line of work to the mixed case, by showing an algorithm solving MILP in time f(a,d)poly(n), where a is the largest coefficient of the constraint matrix, d is its treedepth, and n is the number of variables. |
Cornelius Brand; Martin Koutecký; Sebastian Ordyniak; |
| 433 | NuQClq: An Effective Local Search Algorithm for Maximum Quasi-Clique Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper develops an efficient local search algorithm named NuQClq for the MQCP, which has two main ideas. |
Jiejiang Chen; Shaowei Cai; Shiwei Pan; Yiyuan Wang; Qingwei Lin; Mengyu Zhao; Minghao Yin; |
| 434 | Symmetry Breaking for K-Robust Multi-Agent Path Finding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In thiswork we introducing a variety of pairwise symmetry break-ing constraints, specific tok-robust planning, that can effi-ciently find compatible and optimal paths for pairs of con-flicting agents. |
Zhe Chen; Daniel D. Harabor; Jiaoyang Li; Peter J. Stuckey; |
| 435 | Escaping Local Optima with Non-Elitist Evolutionary Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We solve this open problem through rigorous runtime analysis of elitist and non-elitist population-based EAs on a class of multi-modal problems. |
Duc-Cuong Dang; Anton Eremeev; Per Kristian Lehre; |
| 436 | Pareto Optimization for Subset Selection with Dynamic Partition Matroid Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we consider the subset selection problems with submodular or monotone discrete objective functions under partition matroid constraints where the thresholds are dynamic. |
Anh Viet Do; Frank Neumann; |
| 437 | Theoretical Analyses of Multi-Objective Evolutionary Algorithms on Multi-Modal Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the OneJumpZeroJump problem, a bi-objective problem whose single objectives are isomorphic to the classic jump functions benchmark. |
Benjamin Doerr; Weijie Zheng; |
| 438 | Multi-Objective Submodular Maximization By Regret Ratio Minimization with Theoretical Guarantee Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of minimizing the regret ratio in multi-objective submodular maximization, which is to find at most k solutions to approximate the whole Pareto set as well as possible. |
Chao Feng; Chao Qian; |
| 439 | Choosing The Initial State for Online Replanning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show how such ad hoc solutions can be avoided by integrating the choice of the appropriate initial state into the search process itself. |
Maximilian Fickert; Ivan Gavran; Ivan Fedotov; Jörg Hoffmann; Rupak Majumdar; Wheeler Ruml; |
| 440 | OpEvo: An Evolutionary Method for Tensor Operator Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel evolutionary method, OpEvo, which efficiently explores the search spaces of tensor operators by introducing a topology-aware mutation operation based on q-random walk to leverage the topological structures over the search spaces. |
Xiaotian Gao; Wei Cui; Lintao Zhang; Mao Yang; |
| 441 | Efficient Bayesian Network Structure Learning Via Parameterized Local Search on Topological Orderings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study ordering-based local search, where a solution is described via a topological ordering of the variables. |
Niels Grüttemeier; Christian Komusiewicz; Nils Morawietz; |
| 442 | Enhancing Balanced Graph Edge Partition with Effective Local Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study local search algorithms for this problem to further improve the partition results from existing methods. |
Zhenyu Guo; Mingyu Xiao; Yi Zhou; Dongxiang Zhang; Kian-Lee Tan; |
| 443 | Submodular Span, with Applications to Conditional Data Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an extension to the matroid span problem, we propose the submodular span problem that involves finding a large set of elements with small gain relative to a given query set. |
Lilly Kumari; Jeff Bilmes; |
| 444 | EECBS: A Bounded-Suboptimal Search for Multi-Agent Path Finding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study how to decrease its runtime even further using inadmissible heuristics. |
Jiaoyang Li; Wheeler Ruml; Sven Koenig; |
| 445 | Correlation-Aware Heuristic Search for Intelligent Virtual Machine Provisioning in Cloud Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new Prediction+Optimization method named Correlation-Aware Heuristic Search (CAHS) that is capable of accounting for the uncertainty in unknown parameters and delivering effective solutions to difficult optimization problems. |
Chuan Luo; Bo Qiao; Wenqian Xing; Xin Chen; Pu Zhao; Chao Du; Randolph Yao; Hongyu Zhang; Wei Wu; Shaowei Cai; Bing He; Saravanakumar Rajmohan; Qingwei Lin; |
| 446 | Single Player Monte-Carlo Tree Search Based on The Plackett-Luce Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Plackett-Luce MCTS (PL-MCTS), a path search algorithm based on a probabilistic model over the qualities of successor nodes. |
Felix Mohr; Viktor Bengs; Eyke Hüllermeier; |
| 447 | Policy-Guided Heuristic Search with Guarantees Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we introduce Policy-guided Heuristic Search (PHS), a novel search algorithm that uses both a heuristic function and a policy and has theoretical guarantees on the search loss that relates to both the quality of the heuristic and of the policy. |
Laurent Orseau; Levi H. S. Lelis; |
| 448 | Deep Innovation Protection: Confronting The Credit Assignment Problem in Training Heterogeneous Neural Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a method called Deep Innovation Protection (DIP) that addresses the credit assignment problem in training complex heterogenous neural network models end-to-end for such environments. |
Sebastian Risi; Kenneth O. Stanley; |
| 449 | Weighting-based Variable Neighborhood Search for Optimal Camera Placement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a weighting-based variable neighborhood search (WVNS) algorithm for solving OCP. |
Zhouxing Su; Qingyun Zhang; Zhipeng Lü; Chu-Min Li; Weibo Lin; Fuda Ma; |
| 450 | Multi-Goal Multi-Agent Path Finding Via Decoupled and Integrated Goal Vertex Ordering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce multi-goal multi agent path finding (MG-MAPF) which generalizes the standard discrete multi-agent path finding (MAPF) problem. |
Pavel Surynek; |
| 451 | Bayes DistNet – A Robust Neural Network for Algorithm Runtime Distribution Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend RTD prediction models into the Bayesian setting for the first time. |
Jake Tuero; Michael Buro; |
| 452 | Learning Branching Heuristics for Propositional Model Counting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Neuro#, an approach for learning branching heuristics to improve the performance of exact #SAT solvers on instances from a given family of problems. |
Pashootan Vaezipoor; Gil Lederman; Yuhuai Wu; Chris Maddison; Roger B Grosse; Sanjit A. Seshia; Fahiem Bacchus; |
| 453 | Accelerated Combinatorial Search for Outlier Detection with Provable Bound on Sub-Optimality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we are concerned with their influence on the accuracy of Principal Component Analysis (PCA). |
Guihong Wan; Haim Schweitzer; |
| 454 | Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for The Traveling Salesman Problem Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address the Traveling Salesman Problem (TSP), a famous NP-hard combinatorial optimization problem. |
Jiongzhi Zheng; Kun He; Jianrong Zhou; Yan Jin; Chu-Min Li; |
| 455 | Improving Maximum K-plex Solver Via Second-Order Reduction and Graph Color Bounding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the paper, we develop an exact algorithm, Maplex, for solving this problem in real world graphs practically. |
Yi Zhou; Shan Hu; Mingyu Xiao; Zhang-Hua Fu; |
| 456 | GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose to utilize the self-attention mechanism where we explicitly fuse structural information to learn the dependencies between words with different syntactic distances. |
Wasi Uddin Ahmad; Nanyun Peng; Kai-Wei Chang; |
| 457 | Empirical Regularization for Synthetic Sentence Pairs in Unsupervised Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically study the core training procedure of UNMT to analyze the synthetic sentence pairs obtained from back-translation. |
Xi Ai; Bin Fang; |
| 458 | Segmentation of Tweets with URLs and Its Applications to Sentiment Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the structure of tweets with URLs relative to the content of the Web documents pointed to by the URLs. |
Abdullah Aljebreen; Weiyi Meng; Eduard Dragut; |
| 459 | Unsupervised Opinion Summarization with Content Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. |
Reinald Kim Amplayo; Stefanos Angelidis; Mirella Lapata; |
| 460 | Enhancing Scientific Papers Summarization with Citation Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we redefine the task of scientific papers summarization by utilizing their citation graph and propose a citation graph-based summarization model CGSum which can incorporate the information of both the source paper and its references. |
Chenxin An; Ming Zhong; Yiran Chen; Danqing Wang; Xipeng Qiu; Xuanjing Huang; |
| 461 | Multi-Dimensional Explanation of Target Variables from Documents Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Multi-Target Masker (MTM) to address these shortcomings. |
Diego Antognini; Claudiu Musat; Boi Faltings; |
| 462 | Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the ‘coherence’ of the combined shallow semantic graph. |
Rahul Aralikatte; Mostafa Abdou; Heather C Lent; Daniel Hershcovich; Anders Søgaard; |
| 463 | Segatron: Segment-Aware Transformer for Language Modeling and Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token. |
He Bai; Peng Shi; Jimmy Lin; Yuqing Xie; Luchen Tan; Kun Xiong; Wen Gao; Ming Li; |
| 464 | Learning to Copy Coherent Knowledge for Response Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, this paper proposes a Goal-Oriented Knowledge Copy network, GOKC. |
Jiaqi Bai; Ze Yang; Xinnian Liang; Wei Wang; Zhoujun Li; |
| 465 | Contextualized Rewriting for Text Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate contextualized rewriting, which ingests the entire original document. |
Guangsheng Bao; Yue Zhang; |
| 466 | Knowledge-driven Natural Language Understanding of English Text and Its Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Keeping this in mind, we have introduced a novel knowledge driven semantic representation approach for English text. |
Kinjal Basu; Sarat Chandra Varanasi; Farhad Shakerin; Joaquín Arias; Gopal Gupta; |
| 467 | One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation Without A Complex Pipeline Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we cast Text-to-AMR and AMR-to-Text as a symmetric transduction task and show that by devising a careful graph linearization and extending a pretrained encoder-decoder model, it is possible to obtain state-of-the-art performances in both tasks using the very same seq2seq approach, i.e., SPRING (Symmetric PaRsIng aNd Generation). |
Michele Bevilacqua; Rexhina Blloshmi; Roberto Navigli; |
| 468 | Benchmarking Knowledge-Enhanced Commonsense Question Answering Via Knowledge-to-Text Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. |
Ning Bian; Xianpei Han; Bo Chen; Le Sun; |
| 469 | Multilingual Transfer Learning for QA Using Translation As Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. |
Mihaela Bornea; Lin Pan; Sara Rosenthal; Radu Florian; Avirup Sil; |
| 470 | Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales. |
Faeze Brahman; Vered Shwartz; Rachel Rudinger; Yejin Choi; |
| 471 | Brain Decoding Using FNIRS Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate brain decoding tasks under the help of fNIRS and empirically compare fNIRS with fMRI. |
Lu Cao; Dandan Huang; Yue Zhang; Xiaowei Jiang; Yanan Chen; |
| 472 | Extracting Zero-shot Structured Information from Form-like Documents: Pretraining with Keys and Triggers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit the problem of extracting the values of a given set of key fields from form-like documents. |
Rongyu Cao; Ping Luo; |
| 473 | Simple or Complex? Learning to Predict Readability of Bengali Texts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a readability analysis tool capable of analyzing text written in the Bengali language to provide in-depth information on its readability and complexity. |
Susmoy Chakraborty; Mir Tafseer Nayeem; Wasi Uddin Ahmad; |
| 474 | Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate Att-Input and Att-Output, two alignment-based constrained decoding methods. |
Guanhua Chen; Yun Chen; Victor O.K. Li; |
| 475 | Aspect-Level Sentiment-Controllable Review Generation with Mutual Learning Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a mutual learning framework to take advantage of unlabeled data to assist the aspect-level sentiment-controllable review generation. |
Huimin Chen; Yankai Lin; Fanchao Qi; Jinyi Hu; Peng Li; Jie Zhou; Maosong Sun; |
| 476 | Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we introduce a large-scale multi-domain text corpus for modeling persuasive strategies in good-faith text requests. |
Jiaao Chen; Diyi Yang; |
| 477 | A Lightweight Neural Model for Biomedical Entity Linking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a lightweight neural method for biomedical entity linking, which needs just a fraction of the parameters of a BERT model and much less computing resources. |
Lihu Chen; Gaël Varoquaux; Fabian M. Suchanek; |
| 478 | Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we transform ASTE task into a multi-turn machine reading comprehension (MTMRC) task and propose a bidirectional MRC (BMRC) framework to address this challenge. |
Shaowei Chen; Yu Wang; Jie Liu; Yuelin Wang; |
| 479 | Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose collaborative adversarial training to improve the data utilization, which coordinates virtual adversarial training (VAT) and adversarial training (AT) at different levels. |
Tao Chen; Haochen Shi; Liyuan Liu; Siliang Tang; Jian Shao; Zhigang Chen; Yueting Zhuang; |
| 480 | Reasoning in Dialog: Improving Response Generation By Context Reading Comprehension Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, in this paper, we propose to improve the response generation performance by examining the model’s ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. |
Xiuying Chen; Zhi Cui; Jiayi Zhang; Chen Wei; Jianwei Cui; Bin Wang; Dongyan Zhao; Rui Yan; |
| 481 | Meta-Transfer Learning for Low-Resource Abstractive Summarization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to utilize two knowledge-rich sources to tackle this problem, which are large pre-trained models and diverse existing corpora. |
Yi-Syuan Chen; Hong-Han Shuai; |
| 482 | Adaptive Prior-Dependent Correction Enhanced Reinforcement Learning for Natural Language Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, we propose a technique called adaptive prior-dependent correction (APDC) to enhance RL. |
Wei Cheng; Ziyan Luo; Qiyue Yin; |
| 483 | How Linguistically Fair Are Multilingual Pre-Trained Language Models? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As we discuss in this paper, this is often the case, and the choices are usually made without a clear articulation of reasons or underlying fairness assumptions. |
Monojit Choudhury; Amit Deshpande; |
| 484 | DirectQE: Direct Pretraining for Machine Translation Quality Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel framework called DirectQE that provides a direct pretraining for QE tasks. |
Qu Cui; Shujian Huang; Jiahuan Li; Xiang Geng; Zaixiang Zheng; Guoping Huang; Jiajun Chen; |
| 485 | We Can Explain Your Research in Layman’s Terms: Towards Automating Science Journalism at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to study Automating Science Journalism (ASJ), the process of producing a layman’s terms summary of a research article, as a new benchmark for long neural abstractive summarization and story generation. |
Rumen Dangovski; Michelle Shen; Dawson Byrd; Li Jing; Desislava Tsvetkova; Preslav Nakov; Marin Soljačić; |
| 486 | Consecutive Decoding for Speech-to-text Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce the learning difficulty, we propose COnSecutive Transcription and Translation (COSTT), an integral approach for speech-to-text translation. |
Qianqian Dong; Mingxuan Wang; Hao Zhou; Shuang Xu; Bo Xu; Lei Li; |
| 487 | Listen, Understand and Translate: Triple Supervision Decouples End-to-end Speech-to-text Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Listen-Understand-Translate, (LUT), a unified framework with triple supervision signals to decouple the end-to-end speech-to-text translation task. |
Qianqian Dong; Rong Ye; Mingxuan Wang; Hao Zhou; Shuang Xu; Bo Xu; Lei Li; |
| 488 | MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to evaluate a diverse set of generations, we propose a simple scoring algorithm, based on bipartite graph matching, to optimally incorporate a set of diverse references. |
Yao Dou; Maxwell Forbes; Ari Holtzman; Yejin Choi; |
| 489 | Knowledge-aware Leap-LSTM: Integrating Prior Knowledge Into Leap-LSTM Towards Faster Long Text Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Knowledge-AwareLeap-LSTM (KALL), a novel architecture which integrates prior human knowledge (created either manually or automatically) like in-domain keywords, terminologies or lexicons into Leap-LSTM to partially supervise the skipping process. |
Jinhua Du; Yan Huang; Karo Moilanen; |
| 490 | FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose FILTER, an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. |
Yuwei Fang; Shuohang Wang; Zhe Gan; Siqi Sun; Jingjing Liu; |
| 491 | Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present an innovative model for discontinuous NER based on pointer networks, where the pointer simultaneously decides whether a token at each decoding frame constitutes an entity mention and where the next constituent token is. |
Hao Fei; Donghong Ji; Bobo Li; Yijiang Liu; Yafeng Ren; Fei Li; |
| 492 | Encoder-Decoder Based Unified Semantic Role Labeling with Label-Aware Syntax Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a novel unified SRL framework based on the sequence-to-sequence architecture with double enhancement in both the encoder and decoder sides. |
Hao Fei; Fei Li; Bobo Li; Donghong Ji; |
| 493 | End-to-end Semantic Role Labeling with Neural Transition-based Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the first work of transition-based neural models for end-to-end SRL. |
Hao Fei; Meishan Zhang; Bobo Li; Donghong Ji; |
| 494 | Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we prop |