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

2024/03/07 by Halil Yiğit Öksüz, Fabio Molinari, Oksuz, Halil Yigit +5 · 1 citation
Computer Science · Social Sciences · #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #Privacy, Security, and Data Protection

paper · pdf · doi:10.48550/arxiv.2403.04431

Abstract

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.

Cited by

• Fairness in Federated Learning: Fairness for Whom?

Related

• Over-the-Air Fair Federated Learning via Multi-Objective Optimization
• Over-the-Air Federated Learning In Broadband Communication
• Over-the-Air Federated Learning and Optimization
• Privacy Enhancement in Over-the-Air Federated Learning via Adaptive Receive Scaling
• Fairness and Accuracy in Federated Learning