arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.04431cs.LGcs.CY
收藏

提升空中联邦学习的公平性与鲁棒性

Boosting Fairness and Robustness in Over-the-Air Federated Learning

Technische Universität Berlin(柏林工业大学);Exzellenzcluster Science of Intelligence(科学智能卓越集群)

Halil Yigit Oksuz, Fabio Molinari, Henning Sprekeler, Joerg Raisch

AI总结:

针对超5G场景下空中联邦学习的效率与公平鲁棒性需求,提出基于极小极大优化的算法,借上境图形式证明收敛性,无需复杂编解码重建信道系数,兼顾效率、隐私、公平性与鲁棒性。

摘要:

空中计算(Over-the-Air Computation)是一种超5G通信策略,近期因其高效性被证实可用于机器学习模型的去中心化训练。本文提出一种空中联邦学习算法,旨在通过极小极大(minmax)优化实现公平性与鲁棒性。借助当前问题的上境图(epigraph)形式,我们证明该算法可收敛至极小极大问题的最优解。此外,与现有最优方法不同,所提方法无需通过复杂的编解码方案重建信道系数,这同时提升了效率与隐私性。

英文摘要:

Over-the-Air Computation is a beyond-5G communication strategy that has recently been shown to be useful for the decentralized training of machine learning models due to its efficiency. In this paper, we propose an Over-the-Air federated learning algorithm that aims to provide fairness and robustness through minmax optimization. By using the epigraph form of the problem at hand, we show that the proposed algorithm converges to the optimal solution of the minmax problem. Moreover, the proposed approach does not require reconstructing channel coefficients by complex encoding-decoding schemes as opposed to state-of-the-art approaches. This improves both efficiency and privacy.

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。

↑