Homophily Enhanced Graph Domain Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912405161771008 |
|---|---|
| author | Fang, Ruiyi Li, Bingheng Zhao, Jingyu Pu, Ruizhi Zeng, Qiuhao Xu, Gezheng Ling, Charles Wang, Boyu |
| author_facet | Fang, Ruiyi Li, Bingheng Zhao, Jingyu Pu, Ruizhi Zeng, Qiuhao Xu, Gezheng Ling, Charles Wang, Boyu |
| contents | Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the significance of graph homophily, a pivotal factor for graph domain alignment, which, however, has long been overlooked in existing approaches. Specifically, our analysis first reveals that homophily discrepancies exist in benchmarks. Moreover, we also show that homophily discrepancies degrade GDA performance from both empirical and theoretical aspects, which further underscores the importance of homophily alignment in GDA. Inspired by this finding, we propose a novel homophily alignment algorithm that employs mixed filters to smooth graph signals, thereby effectively capturing and mitigating homophily discrepancies between graphs. Experimental results on a variety of benchmarks verify the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Homophily Enhanced Graph Domain Adaptation Fang, Ruiyi Li, Bingheng Zhao, Jingyu Pu, Ruizhi Zeng, Qiuhao Xu, Gezheng Ling, Charles Wang, Boyu Social and Information Networks Artificial Intelligence Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the significance of graph homophily, a pivotal factor for graph domain alignment, which, however, has long been overlooked in existing approaches. Specifically, our analysis first reveals that homophily discrepancies exist in benchmarks. Moreover, we also show that homophily discrepancies degrade GDA performance from both empirical and theoretical aspects, which further underscores the importance of homophily alignment in GDA. Inspired by this finding, we propose a novel homophily alignment algorithm that employs mixed filters to smooth graph signals, thereby effectively capturing and mitigating homophily discrepancies between graphs. Experimental results on a variety of benchmarks verify the effectiveness of our method. |
| title | Homophily Enhanced Graph Domain Adaptation |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2505.20089 |