Deep Graph-Level Clustering Using Pseudo-Label-Guided Mutual Information Maximization Network

TL;DR

This paper introduces DGLC, a novel deep learning method for clustering entire graphs by learning discriminative representations through mutual information maximization and pseudo-label guidance, achieving state-of-the-art results.

Contribution

The paper proposes a new end-to-end deep graph clustering method that maximizes mutual information and uses pseudo-labels for discriminative graph representations.

Findings

DGLC outperforms existing methods on six benchmark datasets.

The approach effectively learns discriminative graph-level representations.

State-of-the-art clustering performance achieved.

Abstract

In this work, we study the problem of partitioning a set of graphs into different groups such that the graphs in the same group are similar while the graphs in different groups are dissimilar. This problem was rarely studied previously, although there have been a lot of work on node clustering and graph classification. The problem is challenging because it is difficult to measure the similarity or distance between graphs. One feasible approach is using graph kernels to compute a similarity matrix for the graphs and then performing spectral clustering, but the effectiveness of existing graph kernels in measuring the similarity between graphs is very limited. To solve the problem, we propose a novel method called Deep Graph-Level Clustering (DGLC). DGLC utilizes a graph isomorphism network to learn graph-level representations by maximizing the mutual information between the representations of entire graphs and substructures, under the regularization of a clustering module that ensures discriminative representations via pseudo labels. DGLC achieves graph-level representation learning and graph-level clustering in an end-to-end manner. The experimental results on six benchmark datasets of graphs show that our DGLC has state-of-the-art performance in comparison to many baselines.