Struc2vec: Learning Node Representations From Structural Identity

Abstract

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents <i>struc2vec</i>, a novel and flexible framework for learning latent representations for the structural identity of nodes. <i>struc2vec</i> uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while <i>struc2vec</i> exhibits much superior performance in this task, as it overcomes limitations of prior approaches. As a consequence, numerical experiments indicate that <i>struc2vec</i> improves performance on classification tasks that depend more on structural identity.