BriefGPT.xyz
Mar, 2024
提升无线联邦学习中的公平性和鲁棒性
Boosting Fairness and Robustness in Over-the-Air Federated Learning
HTML
PDF
Halil Yigit Oksuz, Fabio Molinari, Henning Sprekeler, Joerg Raisch
TL;DR
我们提出了一种基于Over-the-Air的联邦学习算法，通过最小最大优化以实现公平性和稳健性，无需复杂的编码-解码方案即可收敛于最优解，提高了效率和隐私。
Abstract
over-the-air computation
is a
beyond-5g communication strategy
that has recently been shown to be useful for the
decentralized training
of
→