基本信息
- 来源: arxiv
- 原始来源: https://arxiv.org/abs/2604.03226v1
- 作者: Van Sy Mai, Kushal Chakrabarti, Richard J. La, Dipankar Maity
- 分类: cs.LG
- 论文时间: 2026-04-03T17:51:29Z
- 论文 PDF: https://arxiv.org/pdf/2604.03226v1.pdf
来源摘要/节选
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.
来源说明
当前只保存了官方论文摘要，不代表论文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据，不包含基于旧正文或缺失原文的扩展推断。