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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Oksuz, Halil Yigit, Molinari, Fabio, Sprekeler, Henning, Raisch, Joerg
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917607428325376
author Oksuz, Halil Yigit
Molinari, Fabio
Sprekeler, Henning
Raisch, Joerg
author_facet Oksuz, Halil Yigit
Molinari, Fabio
Sprekeler, Henning
Raisch, Joerg
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting Fairness and Robustness in Over-the-Air Federated Learning
Oksuz, Halil Yigit
Molinari, Fabio
Sprekeler, Henning
Raisch, Joerg
Machine Learning
Computers and Society
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.
title Boosting Fairness and Robustness in Over-the-Air Federated Learning
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2403.04431