Proportional Fairness in Federated Learning

2022/02/03 by Guojun Zhang, Zhang, Guojun, Saber Malekmohammadi +5 · 1 citation
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2202.01666

openalex publication_date 2022/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory performances for each of the numerous diverse clients. In this work, we introduce and study a new fairness notion in FL, called proportional fairness (PF), which is based on the relative change of each client's performance. From its connection with the bargaining games, we propose PropFair, a novel and easy-to-implement algorithm for finding proportionally fair solutions in FL and study its convergence properties. Through extensive experiments on vision and language datasets, we demonstrate that PropFair can approximately find PF solutions, and it achieves a good balance between the average performances of all clients and of the worst 10% clients. Our code is available at \urlhttps://github.com/huawei-noah/Federated-Learning/tree/main/FairFL.

Cited by

• Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning

Related

• Federated Learning with Relative Fairness
• FedGA: A Fair Federated Learning Framework Based on the Gini Coefficient
• Federated Fairness Analytics: Quantifying Fairness in Federated Learning
• FedFair³: Unlocking Threefold Fairness in Federated Learning
• E2FL: Equal and Equitable Federated Learning