Homophily-aware Heterogeneous Graph Contrastive Learning

TL;DR

This paper introduces HGMS, a novel contrastive learning framework for heterogeneous graphs that effectively captures homophily by leveraging connection strength, multi-view self-expression, and innovative augmentation strategies, improving downstream task performance.

Contribution

The paper proposes a new heterophily-aware contrastive learning framework, HGMS, with connection strength-based augmentation and self-expressive learning to better model homophily in heterogeneous graphs.

Findings

HGMS outperforms existing methods on multiple downstream tasks.

The proposed augmentation enhances homophily in graph views.

Self-expressive learning improves false negative identification.

Abstract

Heterogeneous graph pre-training (HGP) has demonstrated remarkable performance across various domains. However, the issue of heterophily in real-world heterogeneous graphs (HGs) has been largely overlooked. To bridge this research gap, we proposed a novel heterogeneous graph contrastive learning framework, termed HGMS, which leverages connection strength and multi-view self-expression to learn homophilous node representations. Specifically, we design a heterogeneous edge dropping augmentation strategy that enhances the homophily of augmented views. Moreover, we introduce a multi-view self-expressive learning method to infer the homophily between nodes. In practice, we develop two approaches to solve the self-expressive matrix. The solved self-expressive matrix serves as an additional augmented view to provide homophilous information and is used to identify false negatives in contrastive loss. Extensive experimental results demonstrate the superiority of HGMS across different downstream tasks.