HomoGCL: Rethinking Homophily in Graph Contrastive Learning

TL;DR

HomoGCL is a novel framework that enhances graph contrastive learning by explicitly leveraging homophily, expanding positive samples with neighbor nodes, and achieving state-of-the-art results across multiple datasets.

Contribution

The paper introduces HomoGCL, a model-agnostic framework that explicitly incorporates homophily into graph contrastive learning, improving performance and theoretical bounds.

Findings

HomoGCL achieves state-of-the-art results on six datasets.

It consistently improves existing graph CL methods.

Theoretical analysis shows a tighter mutual information lower bound.

Abstract

Contrastive learning (CL) has become the de-facto learning paradigm in self-supervised learning on graphs, which generally follows the "augmenting-contrasting" learning scheme. However, we observe that unlike CL in computer vision domain, CL in graph domain performs decently even without augmentation. We conduct a systematic analysis of this phenomenon and argue that homophily, i.e., the principle that "like attracts like", plays a key role in the success of graph CL. Inspired to leverage this property explicitly, we propose HomoGCL, a model-agnostic framework to expand the positive set using neighbor nodes with neighbor-specific significances. Theoretically, HomoGCL introduces a stricter lower bound of the mutual information between raw node features and node embeddings in augmented views. Furthermore, HomoGCL can be combined with existing graph CL models in a plug-and-play way with light extra computational overhead. Extensive experiments demonstrate that HomoGCL yields multiple state-of-the-art results across six public datasets and consistently brings notable performance improvements when applied to various graph CL methods. Code is avilable at https://github.com/wenzhilics/HomoGCL.