EUVIMEDEUVIMED entdecken
Crossref

Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity

Shiyuan Zuo, Xingrun Yan, Rongfei Fan, Han Hu, Hangguan Shan, Tony Q. S. Quek, Puning Zhao

IEEE Transactions on Mobile Computing · 2025-10 · 24 (10) · 10729-10742

DOI: 10.1109/tmc.2025.3571058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-10. Verfasst von Shiyuan Zuo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Joint Funds of the National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper addresses federated learning (FL) in the context of malicious Byzantine attacks and data heterogeneity. We introduce a novel Robust Average Gradient Algorithm (RAGA), which uses the geometric median for aggregation and allows flexible round number for local updates. Unlike most existing resilient approaches, which base their convergence analysis on strongly-convex loss functions or homogeneously distributed datasets, this work conducts convergence analysis for both strongly-convex and non-convex loss functions over heterogeneous datasets. The theoretical analysis indicates that as long as the fraction of the data from malicious users is less than half, RAGA can achieve convergence at a rate of $\mathcal {O}({1}/{T^{2/3- \delta }})$ O ( 1 / T 2 / 3 - δ ) for non-convex loss functions, where $T$ T is the iteration number and $\delta \in (0, 2/3)$ δ ∈ ( 0 , 2 / 3 ) . For strongly-convex loss functions, the convergence rate is linear. Furthermore, the stationary point or global optimal solution is shown to be attainable as data heterogeneity diminishes. Experimental results validate the robustness of RAGA against Byzantine attacks and demonstrate its superior convergence performance compared to baselines under varying intensities of Byzantine attacks on heterogeneous datasets.

Förderung

  • Joint Funds of the National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Zuo, S., Yan, X., Fan, R., Hu, H., Shan, H., Quek, T. Q. S., & Zhao, P. (2025). Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity. IEEE Transactions on Mobile Computing, 24(10), 10729-10742. https://doi.org/10.1109/tmc.2025.3571058

Vancouver

Zuo S, Yan X, Fan R, Hu H, Shan H, Quek TQS, et al. Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity. IEEE Transactions on Mobile Computing. 2025;24(10):10729-10742. doi:10.1109/tmc.2025.3571058

BibTeX
@article{Zuo2025,
  author = {Zuo, Shiyuan and Yan, Xingrun and Fan, Rongfei and Hu, Han and Shan, Hangguan and Quek, Tony Q. S. and Zhao, Puning},
  title = {Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {10},
  pages = {10729--10742},
  doi = {10.1109/tmc.2025.3571058}
}
Kostenlos starten →