Homophily Enhanced Graph Domain Adaptation

Ruiyi Fang, Bingheng Li, Jingyu Zhao, Ruizhi Pu, Qiuhao Zeng, Gezheng Xu, Charles Ling, Boyu Wang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16006-16028, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-fang25g, title = {Homophily Enhanced Graph Domain Adaptation}, author = {Fang, Ruiyi and Li, Bingheng and Zhao, Jingyu and Pu, Ruizhi and Zeng, Qiuhao and Xu, Gezheng and Ling, Charles and Wang, Boyu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {16006--16028}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/fang25g/fang25g.pdf}, url = {https://proceedings.mlr.press/v267/fang25g.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Homophily Enhanced Graph Domain Adaptation %A Ruiyi Fang %A Bingheng Li %A Jingyu Zhao %A Ruizhi Pu %A Qiuhao Zeng %A Gezheng Xu %A Charles Ling %A Boyu Wang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-fang25g %I PMLR %P 16006--16028 %U https://proceedings.mlr.press/v267/fang25g.html %V 267 %X 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.
APA
Fang, R., Li, B., Zhao, J., Pu, R., Zeng, Q., Xu, G., Ling, C. & Wang, B.. (2025). Homophily Enhanced Graph Domain Adaptation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:16006-16028 Available from https://proceedings.mlr.press/v267/fang25g.html.

Related Material