FairMean:分布式学习中应对标签投毒的公平性方法
FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks
分布式训练里投毒攻击会让公平性机制反被利用,这篇论文给出加权方案,理论证明加实验都有,做联邦学习的人可以看看。
arXiv 论文提出 FairMean,用有界非递减的损失函数为客户端梯度加权,以化解公平性与鲁棒性的冲突。权重随本地损失增加而上升,可优先照顾高损失客户端,上限则防止被投毒客户端的梯度被过度放大。
论文证明在无标签投毒时,最小化 FairMean 目标比标准平均损失目标更有利于解的公平性;在投毒场景下建立了平均平稳性界,其攻击相关项与被投毒客户端占比的平方成正比。
实验显示 FairMean 能降低准确率方差并提升最差客户端的准确率。
FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include FairMean, federated learning, distributed learning, AI safety.
Source attribution: curated from arXiv cs.AI (@Huigan Zheng, Jiaojiao Zhang, Yongxiang Liu).