Deep node clustering based on mutual information maximization

Abstract

Variational Graph Autoencoders (VGAs) are generative models for unsupervised learning of node representations within graph data. While VGAs have been achieved state-of-the-art results for different predictive tasks on graph-structured data, they are susceptible to the over-pruning problem where only a small subset of the stochastic latent units are active. This can limit their modeling capacity and their ability to learn meaningful representations. In this paper, we present SOLI (Stacked auto-encoder for nOde cLusterIng), an information maximization approach for learning graph representations by leveraging maximal cliques. SOLI relies on aggregating useful representations by assigning clique-based weights to various edges in a neighborhood while maximizing mutual information. The learned representations are mindful of graph patches centered around each node, and can be used for a range of downstream tasks, and thus encouraging more active units. We demonstrate strong performance across three graph benchmark datasets.(Code is available at https://github.com/SoheilaMolaei/SOLI.)