The Cost of Local and Global Fairness in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duan, Yuying, Xu, Gelei, Shi, Yiyu, Lemmon, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910900171046912
author Duan, Yuying
Xu, Gelei
Shi, Yiyu
Lemmon, Michael
author_facet Duan, Yuying
Xu, Gelei
Shi, Yiyu
Lemmon, Michael
contents With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of fairness are important in FL: global and local fairness. Global fairness addresses the disparity across the entire population and local fairness is concerned with the disparity within each client. Prior fair FL frameworks have improved either global or local fairness without considering both. Furthermore, while the majority of studies on fair FL focuses on binary settings, many real-world applications are multi-class problems. This paper proposes a framework that investigates the minimum accuracy lost for enforcing a specified level of global and local fairness in multi-class FL settings. Our framework leads to a simple post-processing algorithm that derives fair outcome predictors from the Bayesian optimal score functions. Experimental results show that our algorithm outperforms the current state of the art (SOTA) with regard to the accuracy-fairness tradoffs, computational and communication costs. Codes are available at: https://github.com/papersubmission678/The-cost-of-local-and-global-fairness-in-FL .
format Preprint
id arxiv_https___arxiv_org_abs_2503_22762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Cost of Local and Global Fairness in Federated Learning
Duan, Yuying
Xu, Gelei
Shi, Yiyu
Lemmon, Michael
Machine Learning
Artificial Intelligence
Computers and Society
With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of fairness are important in FL: global and local fairness. Global fairness addresses the disparity across the entire population and local fairness is concerned with the disparity within each client. Prior fair FL frameworks have improved either global or local fairness without considering both. Furthermore, while the majority of studies on fair FL focuses on binary settings, many real-world applications are multi-class problems. This paper proposes a framework that investigates the minimum accuracy lost for enforcing a specified level of global and local fairness in multi-class FL settings. Our framework leads to a simple post-processing algorithm that derives fair outcome predictors from the Bayesian optimal score functions. Experimental results show that our algorithm outperforms the current state of the art (SOTA) with regard to the accuracy-fairness tradoffs, computational and communication costs. Codes are available at: https://github.com/papersubmission678/The-cost-of-local-and-global-fairness-in-FL .
title The Cost of Local and Global Fairness in Federated Learning
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2503.22762