F3: Fair and Federated Face Attribute Classification with Heterogeneous Data

TL;DR

This paper introduces F3, a federated learning framework designed to achieve fair face attribute classification across diverse demographic groups without assuming data homogeneity, balancing accuracy and fairness.

Contribution

F3 is the first federated learning approach that enhances fairness in face attribute classification under heterogeneous data conditions.

Findings

F3 improves fairness across demographic groups in face datasets.

F3 maintains competitive accuracy while enhancing fairness.

Empirical results validate F3's effectiveness in real-world scenarios.

Abstract

Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Apart from this trend, Federated Learning (FL) is increasingly gaining traction as a scalable paradigm for distributed training. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is too restrictive in real-world settings. We propose F3, a novel FL framework for fair FAC under data heterogeneity. F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption. We demonstrate the efficacy of F3 by reporting empirically observed fairness measures and accuracy guarantees on popular face datasets. Our results suggest that F3 strikes a practical balance between accuracy and fairness for FAC.