Evaluation of cross-silo federated graph learning under data heterogeneity

Jin YU; Junping DU; Zhe XUE; Yi LIU

doi:10.1007/s11704-025-50666-9

Front. Comput. Sci. ›› 2027, Vol. 21 ›› Issue (1) :2101314 DOI: 10.1007/s11704-025-50666-9

Artificial Intelligence

LETTER

Evaluation of cross-silo federated graph learning under data heterogeneity

Author information +

History +

PDF (546KB)

Graphical abstract

Cite this article

Download citation ▾

Jin YU, Junping DU, Zhe XUE, Yi LIU. Evaluation of cross-silo federated graph learning under data heterogeneity. Front. Comput. Sci., 2027, 21(1): 2101314 DOI:10.1007/s11704-025-50666-9

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Verma D C, White G, Julier S, Pasteris S, Chakraborty S, Cirincione G. Approaches to address the data skew problem in federated learning. In: Proceedings of SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications. 2019, 542−557

[2]	Sheng T, Shen C, Liu Y, Ou Y, Qu Z, Liang Y, Wang J . Modeling global distribution for federated learning with label distribution skew. Pattern Recognition, 2023, 143: 109724

[3]	Bojchevski A, Günnemann S. Adversarial attacks on node embeddings via graph poisoning. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 695−704

[4]	Baek J, Jeong W, Jin J, Yoon J, Hwang S J. Personalized subgraph federated learning. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 58

[5]	Bettinelli M, Benoit A, Grandjean K. Discovering communities with clustered federated learning. In: Proceedings of the IEEE International Conference on Big Data (BigData). 2024, 7648−7657