Federated Learning at the Forefront of Fairness: A Multifaceted Perspective

TL;DR

This paper provides a comprehensive survey of fairness-aware approaches in federated learning, categorizing methods, evaluating metrics, and outlining future research directions to enhance equitable model performance across diverse clients.

Contribution

It offers a multifaceted classification framework for fairness in federated learning, integrating performance and capability perspectives, and discusses evaluation metrics and future research avenues.

Findings

Classified state-of-the-art fairness approaches in FL

Analyzed effectiveness of various fairness metrics

Outlined open challenges and future directions

Abstract

Fairness in Federated Learning (FL) is emerging as a critical factor driven by heterogeneous clients' constraints and balanced model performance across various scenarios. In this survey, we delineate a comprehensive classification of the state-of-the-art fairness-aware approaches from a multifaceted perspective, i.e., model performance-oriented and capability-oriented. Moreover, we provide a framework to categorize and address various fairness concerns and associated technical aspects, examining their effectiveness in balancing equity and performance within FL frameworks. We further examine several significant evaluation metrics leveraged to measure fairness quantitatively. Finally, we explore exciting open research directions and propose prospective solutions that could drive future advancements in this important area, laying a solid foundation for researchers working toward fairness in FL.