GLCC: A General Framework for Graph-Level Clustering

TL;DR

This paper introduces GLCC, a novel framework for graph-level clustering across multiple graphs, leveraging contrastive learning and adaptive affinity graphs to improve clustering performance in bioinformatics applications.

Contribution

The paper proposes a general graph-level clustering framework that integrates instance- and cluster-level contrastive learning for multiple graphs, a novel approach in this domain.

Findings

GLCC outperforms existing methods on various datasets.

Adaptive affinity graph enhances clustering quality.

Contrastive learning improves representation learning.

Abstract

This paper studies the problem of graph-level clustering, which is a novel yet challenging task. This problem is critical in a variety of real-world applications such as protein clustering and genome analysis in bioinformatics. Recent years have witnessed the success of deep clustering coupled with graph neural networks (GNNs). However, existing methods focus on clustering among nodes given a single graph, while exploring clustering on multiple graphs is still under-explored. In this paper, we propose a general graph-level clustering framework named Graph-Level Contrastive Clustering (GLCC) given multiple graphs. Specifically, GLCC first constructs an adaptive affinity graph to explore instance- and cluster-level contrastive learning (CL). Instance-level CL leverages graph Laplacian based contrastive loss to learn clustering-friendly representations while cluster-level CL captures discriminative cluster representations incorporating neighbor information of each sample. Moreover, we utilize neighbor-aware pseudo-labels to reward the optimization of representation learning. The two steps can be alternatively trained to collaborate and benefit each other. Experiments on a range of well-known datasets demonstrate the superiority of our proposed GLCC over competitive baselines.