arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.04432cs.LGmath.OC
收藏

联邦学习中拜占庭客户端数量估计的权衡

Trade-off in Estimating the Number of Byzantine Clients in Federated Learning

Department of Computer Science University of Maryland College Park(计算机科学系大学马里兰大学学院公园)

Ziyi Chen, Su Zhang, Heng Huang

AI总结:

本文理论分析联邦学习中估计拜占庭客户端数量对聚合器及联邦学习性能的影响,揭示低估导致性能任意差,非低估时误差与鲁棒程度成正比,存在权衡。

摘要:

联邦学习在近期的大规模优化和机器学习研究与应用中日益受到关注,但它也容易受到可能发送任何错误信号的拜占庭客户端的影响。鲁棒聚合器通常用于抵抗拜占庭客户端。这通常需要估计未知的拜占庭客户端数量 $f$,并据此选择具有适当鲁棒性程度(即聚合器允许的最大拜占庭客户端数量 $\hat{f}$)的聚合器。这种估计应对性能产生重要影响,但据我们所知,尚未有系统研究。这项工作将通过理论分析聚合器的最坏情况误差及其在 $\hat{f}$ 和 $f$ 的任何情况下的联邦学习算法来填补这一空白。具体来说,我们将证明低估($\hat{f}<f$)可能导致聚合器和联邦学习的性能任意差。对于非低估($\hat{f}\ge f$),我们证明了聚合器和联邦学习误差的相同阶的最优下界和上界。所有这些最优界都与 $\hat{f}/(n-f-\hat{f})$ 成正比,其中 $n$ 为客户端数量,该值随 $\hat{f}$ 增大而单调增加。这表明一个基本权衡:虽然具有更大鲁棒性程度 $\hat{f}$ 的聚合器可以解决更广泛范围 $f\in [0,\hat{f}]$ 的联邦学习问题,但当实际拜占庭客户端较少甚至没有(即 $f\in [0,\hat{f})$)时,性能可能会恶化。

英文摘要:

Federated learning has attracted increasing attention at recent large-scale optimization and machine learning research and applications, but is also vulnerable to Byzantine clients that can send any erroneous signals. Robust aggregators are commonly used to resist Byzantine clients. This usually requires to estimate the unknown number $f$ of Byzantine clients, and thus accordingly select the aggregators with proper degree of robustness (i.e., the maximum number $\hat{f}$ of Byzantine clients allowed by the aggregator). Such an estimation should have important effect on the performance, which has not been systematically studied to our knowledge. This work will fill in the gap by theoretically analyzing the worst-case error of aggregators as well as its induced federated learning algorithm for any cases of $\hat{f}$ and $f$. Specifically, we will show that underestimation ($\hat{f}<f$) can lead to arbitrarily poor performance for both aggregators and federated learning. For non-underestimation ($\hat{f}\ge f$), we have proved optimal lower and upper bounds of the same order on the errors of both aggregators and federated learning. All these optimal bounds are proportional to $\hat{f}/(n-f-\hat{f})$ with $n$ clients, which monotonically increases with larger $\hat{f}$. This indicates a fundamental trade-off: while an aggregator with a larger robustness degree $\hat{f}$ can solve federated learning problems of wider range $f\in [0,\hat{f}]$, the performance can deteriorate when there are actually fewer or even no Byzantine clients (i.e., $f\in [0,\hat{f})$).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑