Homophily-aware Heterogeneous Graph Contrastive Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929676605194240 |
|---|---|
| author | Wang, Haosen Shi, Chenglong Xu, Can Yan, Surong Tang, Pan |
| author_facet | Wang, Haosen Shi, Chenglong Xu, Can Yan, Surong Tang, Pan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Homophily-aware Heterogeneous Graph Contrastive Learning Wang, Haosen Shi, Chenglong Xu, Can Yan, Surong Tang, Pan Machine Learning Social and Information Networks 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. |
| title | Homophily-aware Heterogeneous Graph Contrastive Learning |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2501.08538 |