Fair Wireless Federated Learning Through the Identification of a Common Descent Direction

In Federated Learning (FL), varying local dataset distributions among clients can result in unsatisfactory performance for some, leading to an unfair model. While some prior works attempted to resolve this issue, their approaches fall short of training a fair model in real-world scenarios where impe...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters 2024-03, Vol.28 (3), p.567-571
Main Authors: Mohajer Hamidi, Shayan, Damen, Oussama
Format: Article
Language:English
Subjects:
Algorithms
Channels
Defects
fairness
Federated learning
Linear programming
Method of moments
Minimization
multi-objective optimization
Noise measurement
Performance evaluation
Servers
Training
Wireless communication
wireless communications
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In Federated Learning (FL), varying local dataset distributions among clients can result in unsatisfactory performance for some, leading to an unfair model. While some prior works attempted to resolve this issue, their approaches fall short of training a fair model in real-world scenarios where imperfections in wireless channels cause the server to receive noisy versions of local updates. To tackle this issue, in this letter, we treat FL as a multi-objective minimization problem, and develop a fair FL algorithm that explicitly accounts for the inherent imperfections of wireless channels. Particularly, we modify the classical multiple gradient descent algorithm to assist the server in identifying a common descent direction for all local objectives based on the received noisy gradients. Additionally, we evaluate the performance of the proposed method via some experiments.
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2024.3350378