FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks

2026-09-22

AI Summary

为解决标签中毒攻击下分布式学习中的公平性与鲁棒性冲突，提出FairMean方法，通过限制加权函数来平衡高损失客户端的影响。

Abstract

Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing a fairness--robustness conflict. We propose FairMean to manage this conflict. FairMean weights client gradients using a bounded, nondecreasing function of local loss. The increasing weights prioritize high-loss clients to promote fairness, while the upper bound prevents excessive loss-induced amplification of poisoned-client gradients. In the absence of label poisoning, we show that minimizing the FairMean objective is more conducive to solution fairness than minimizing the standard average-loss objective. Under label poisoning, we establish an average-stationarity bound whose attack-dependent term is proportional to the square of the poisoned-client fraction. Experiments show that FairMean promotes fairness by reducing accuracy variance while improving worst-client accuracy.

Problem

• fairness
• distributed learning
• label poisoning
• performance disparities

Innovation

• FairMean
• Distributed Learning
• Label Poisoning
• Fairness
• Gradient Weighting