EUVIMEDEUVIMED entdecken
Crossref

Personalized Federated Learning With Transparent Inter-Client Contribution

Yunfeng Zhao, Guoxian Yu, Jun Wang, Lizhen Cui, Dong Wu, Dong Zhang, Carlotta Domeniconi

IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 23748-23760

DOI: 10.1109/tmc.2026.3731148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Yunfeng Zhao und 6 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) has expanded the scope of distributed machine learning by training a global model through the amalgamation of knowledge from various distributed clients. However, the challenge of non-i.i.d. local datasets among clients introduces statistical heterogeneity, thereby compromising the performance of a single global model. Personalized federated learning (PFL) seeks to mitigate this issue by training individualized models tailored for each client. Despite the improved performance achieved by PFL, current approaches lack interpretability in quantifying the significance of inter-client contributions. Furthermore, they often pursue individual models at clients while performing model aggregation to obtain a single global model at the FL server, which still struggles to effectively capture the distinctions among clients. In response to these problems, we propose the personalized Federated learning with Transparent Inter-client Contribution (pFedTIC) approach. Specifically, pFedTIC embraces a dual-level personalized model aggregation strategy to derive an individualized model for each client, and assesses inter-client contribution with the aggregation weights for enhancing transparency. It conducts model aggregation at both the server and client sides using the similarity of model parameters and learning representations, mutual contributions between clients, and model performance. Theoretical analyses are derived to establish the non-convex convergence rate of pFedTIC. Experimental results on benchmark datasets demonstrate its superiority over competitive methods, affirming its effectiveness in handling data heterogeneity. Moreover, the experiments also showcase its capability to interpret inter-client contributions, fostering more transparent FL collaborations.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Shandong Provincial Natural Science Foundation
  • Taishan Scholars Program

Zitieren

APA

Zhao, Y., Yu, G., Wang, J., Cui, L., Wu, D., Zhang, D., & Domeniconi, C. (2026). Personalized Federated Learning With Transparent Inter-Client Contribution. IEEE Transactions on Mobile Computing, 25(12), 23748-23760. https://doi.org/10.1109/tmc.2026.3731148

Vancouver

Zhao Y, Yu G, Wang J, Cui L, Wu D, Zhang D, et al. Personalized Federated Learning With Transparent Inter-Client Contribution. IEEE Transactions on Mobile Computing. 2026;25(12):23748-23760. doi:10.1109/tmc.2026.3731148

BibTeX
@article{Zhao2026,
  author = {Zhao, Yunfeng and Yu, Guoxian and Wang, Jun and Cui, Lizhen and Wu, Dong and Zhang, Dong and Domeniconi, Carlotta},
  title = {Personalized Federated Learning With Transparent Inter-Client Contribution},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {12},
  pages = {23748--23760},
  doi = {10.1109/tmc.2026.3731148}
}
Kostenlos starten →