Structure-enhanced Contrastive Learning for Graph Clustering

TL;DR

This paper introduces SECL, a novel graph clustering method that leverages inherent network structures and a contrastive learning framework to improve clustering accuracy without relying heavily on data augmentation.

Contribution

SECL proposes a structure-enhanced contrastive learning framework that incorporates structural information and modularity maximization for improved graph clustering.

Findings

Outperforms state-of-the-art methods on six datasets

Enhances node embeddings without complex data augmentation

Effectively captures higher-order community structures

Abstract

Graph clustering is a crucial task in network analysis with widespread applications, focusing on partitioning nodes into distinct groups with stronger intra-group connections than inter-group ones. Recently, contrastive learning has achieved significant progress in graph clustering. However, most methods suffer from the following issues: 1) an over-reliance on meticulously designed data augmentation strategies, which can undermine the potential of contrastive learning. 2) overlooking cluster-oriented structural information, particularly the higher-order cluster(community) structure information, which could unveil the mesoscopic cluster structure information of the network. In this study, Structure-enhanced Contrastive Learning (SECL) is introduced to addresses these issues by leveraging inherent network structures. SECL utilizes a cross-view contrastive learning mechanism to enhance node embeddings without elaborate data augmentations, a structural contrastive learning module for ensuring structural consistency, and a modularity maximization strategy for harnessing clustering-oriented information. This comprehensive approach results in robust node representations that greatly enhance clustering performance. Extensive experiments on six datasets confirm SECL's superiority over current state-of-the-art methods, indicating a substantial improvement in the domain of graph clustering.