Enhancing Homophily in Heterogeneous Graph Contrastive Learning via Connection Strength and Multi-view Self-Expression

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 neglected. 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, which preferentially preserves metapath-based edges with strong connection strength, thereby improving the homophily of augmented views. Moreover, we propose a multi-view self-expressive learning method to infer the homophily between nodes from the subspace. 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 mitigate false negatives in contrastive loss. Extensive experimental results demonstrate the superiority of HGMS across different downstream tasks. The code is available at https://github.com/senllh/HGMS/tree/main.