Abstract:Federated Learning (FL) enables clients to collaboratively train a global model without sharing their private data. However, the presence of malicious (Byzantine) clients poses significant challenges to the robustness of FL, particularly when data distributions across clients are heterogeneous. In this paper, we propose a novel Byzantine-robust FL optimization problem that incorporates adaptive weighting into the aggregation process. Unlike conventional approaches, our formulation treats aggregation weights as learnable parameters, jointly optimizing them alongside the global model parameters. To solve this optimization problem, we develop an alternating minimization algorithm with strong convergence guarantees under adversarial attack. We analyze the Byzantine resilience of the proposed objective. We evaluate the performance of our algorithm against state-of-the-art Byzantine-robust FL approaches across various datasets and attack scenarios. Experimental results demonstrate that our method consistently outperforms existing approaches, particularly in settings with highly heterogeneous data and a large proportion of malicious clients.
| Comments: | ICLR 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2511.03529 [cs.LG] |
| (or arXiv:2511.03529v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2511.03529 arXiv-issued DOI via DataCite |
From: Javad Parsa [view email]
[v1]
Wed, 5 Nov 2025 15:02:21 UTC (362 KB)
[v2]
Mon, 25 May 2026 15:35:30 UTC (305 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。