Deep Graph-Level Clustering Using Pseudo-Label-Guided Mutual Information Maximization Network
This addresses a rarely studied problem in graph analysis, offering a novel approach for researchers in machine learning and data mining, though it is incremental as it builds on existing graph representation techniques.
The paper tackles the problem of graph-level clustering, which partitions graphs into groups based on similarity, by proposing DGLC, a method that learns graph-level representations using mutual information maximization and pseudo-label regularization, achieving state-of-the-art performance on six benchmark datasets.
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.