Deep node clustering based on mutual information maximization

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...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2021-09, Vol.455, p.274-282
Main Authors: Molaei, Soheila, Ghanbari Bousejin, Nima, Zare, Hadi, Jalili, Mahdi
Format: Article
Language:English
Subjects:
Graph auto-encoder
Graph neural network
Graph representation learning
Link prediction
Node clustering
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.)
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.03.020