Anomaly Detection With Robust Deep Autoencoders

Abstract

Deep autoencoders, and other deep neural networks, have demonstrated their effectiveness in discovering non-linear features across many problem domains. However, in many real-world problems, large outliers and pervasive noise are commonplace, and one <i>may not have access to clean training data</i> as required by standard deep denoising autoencoders. Herein, we demonstrate novel extensions to deep autoencoders which not only maintain a deep autoencoders' ability to discover high quality, non-linear features but can also eliminate outliers and noise <i>without access to any clean training data</i>. Our model is inspired by Robust Principal Component Analysis, and we split the input data <i>X</i> into two parts, $X = L_{D} + S$, where $L_{D}$ can be effectively reconstructed by a deep autoencoder and $S$ contains the outliers and noise in the original data <i>X</i>. Since such splitting increases the robustness of standard deep autoencoders, we name our model a "Robust Deep Autoencoder (RDA)". Further, we present generalizations of our results to grouped sparsity norms which allow one to distinguish random anomalies from other types of structured corruptions, such as a collection of features being corrupted across many instances or a collection of instances having more corruptions than their fellows. Such "Group Robust Deep Autoencoders (GRDA)" give rise to novel anomaly detection approaches whose superior performance we demonstrate on a selection of benchmark problems.