Byrd-NAFL：融合 Nesterov 动量的拜占庭鲁棒联邦学习

View PDF HTML (experimental)

Abstract:We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To improve communication efficiency while retaining resilience against such adversaries, we propose a Byzantine-resilient Nesterov-augmented federated learning (Byrd-NAFL) algorithm. Byrd-NAFL applies Nesterov's momentum at the server to the output of any soft $\gamma$-Byzantine resilient aggregation rule, while each worker only computes and uploads a stochastic gradient, which keeps the workers stateless, as desired for intermittently participating Internet of Things devices. For smooth non-convex losses, we establish a finite-time convergence guarantee for all momentum factors $\beta\in[0,1)$ without requiring the aggregated gradient to be unbiased or bounded; the bound reduces to that of Byzantine-resilient stochastic gradient descent at $\beta=0$ and is tighter than that of server-side heavy-ball momentum. Experiments on MNIST, CIFAR-10, and Sentiment140 show that Byrd-NAFL converges faster and attains higher accuracy than existing benchmarks in most i.i.d. and non-i.i.d. setups under diverse attacks, while its resilience is bounded by that of the underlying aggregation rule.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2511.02657 [cs.LG]
	(or arXiv:2511.02657v4 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2511.02657 arXiv-issued DOI via DataCite

Submission history

From: Lihan Xu [view email]
[v1] Tue, 4 Nov 2025 15:34:59 UTC (4,310 KB)
[v2] Thu, 3 Sep 2026 12:20:03 UTC (1,506 KB)
[v3] Tue, 13 Oct 2026 14:04:33 UTC (1,564 KB)
[v4] Wed, 14 Oct 2026 06:25:03 UTC (1,564 KB)