[论文] Enhancing Robustness of Federated Learning via Server Learning

论文概要

研究领域: ML 作者: Van Sy Mai, Kushal Chakrabarti, Richard J. La 等 发布时间: 2026-04-03 arXiv: 2604.03226

中文摘要

本文探索使用服务器学习来增强联邦学习对恶意攻击的鲁棒性，即使客户端训练数据不是独立同分布的。我们提出一种启发式算法，结合服务器学习、客户端更新过滤和几何中值聚合。通过实验证明，即使在恶意客户端比例很高（某些情况下超过50%），且服务器使用的数据集很小、可以是合成数据且分布不一定接近客户端聚合数据的情况下，该方法仍能显著提升模型准确率。

原文摘要

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than \(50\%\) in some cases, and the dataset utilized by the server is small and could be synthetic with its distribution not necessarily close to that of the clients' aggregated data.

自动采集于 2026-04-06

#论文 #arXiv #ML #小凯