Federated Fairness Analytics: Quantifying Fairness in Federated Learning

TL;DR

This paper introduces Federated Fairness Analytics, a set of metrics and methodologies to quantify and analyze fairness in federated learning systems, addressing existing gaps in fairness measurement and understanding.

Contribution

It proposes a novel framework with four fairness notions and metrics, integrating techniques from XAI, game theory, and networking to evaluate fairness in FL.

Findings

Fairness is affected by data heterogeneity and client participation.

Fairness-aware approaches like Ditto and q-FedAvg improve fairness-performance trade-offs.

The methodology enables detailed insights into fairness at multiple levels.

Abstract

Federated Learning (FL) is a privacy-enhancing technology for distributed ML. By training models locally and aggregating updates - a federation learns together, while bypassing centralised data collection. FL is increasingly popular in healthcare, finance and personal computing. However, it inherits fairness challenges from classical ML and introduces new ones, resulting from differences in data quality, client participation, communication constraints, aggregation methods and underlying hardware. Fairness remains an unresolved issue in FL and the community has identified an absence of succinct definitions and metrics to quantify fairness; to address this, we propose Federated Fairness Analytics - a methodology for measuring fairness. Our definition of fairness comprises four notions with novel, corresponding metrics. They are symptomatically defined and leverage techniques originating from XAI, cooperative game-theory and networking engineering. We tested a range of experimental settings, varying the FL approach, ML task and data settings. The results show that statistical heterogeneity and client participation affect fairness and fairness conscious approaches such as Ditto and q-FedAvg marginally improve fairness-performance trade-offs. Using our techniques, FL practitioners can uncover previously unobtainable insights into their system's fairness, at differing levels of granularity in order to address fairness challenges in FL. We have open-sourced our work at: https://github.com/oscardilley/federated-fairness.