FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
Li Zhang, Zhongxuan Han, Xiaohua Feng, Jiaming Zhang, Yuyuan Li, Chaochao Chen
TL;DR
FedFACT tackles the dual challenge of achieving global and local group fairness in multiclass federated learning under non-decomposable fairness criteria. It derives Bayes-optimal fair classifiers and provides two complementary paths: in-processing via personalized cost-sensitive learning and post-processing via a plug-in bilevel calibration, each with convergence and generalization guarantees. The framework enables a tunable accuracy–fairness trade-off and demonstrates state-of-the-art performance across diverse, heterogeneous datasets. This work advances privacy-preserving, fair decision-making in distributed settings and offers practical tools for deploying multiclass, group-fair FL systems.
Abstract
With the emerging application of Federated Learning (FL) in decision-making scenarios, it is imperative to regulate model fairness to prevent disparities across sensitive groups (e.g., female, male). Current research predominantly focuses on two concepts of group fairness within FL: Global Fairness (overall model disparity across all clients) and Local Fairness (the disparity within each client). However, the non-decomposable, non-differentiable nature of fairness criteria poses two fundamental, unresolved challenges for fair FL: (i) Harmonizing global and local fairness, especially in multi-class setting; (ii) Enabling a controllable, optimal accuracy-fairness trade-off. To tackle these challenges, we propose a novel controllable federated group-fairness calibration framework, named FedFACT. FedFACT identifies the Bayes-optimal classifiers under both global and local fairness constraints, yielding models with minimal performance decline while guaranteeing fairness. Building on the characterization of the optimal fair classifiers, we reformulate fair federated learning as a personalized cost-sensitive learning problem for in-processing and a bi-level optimization for post-processing. Theoretically, we provide convergence and generalization guarantees for FedFACT to approach the near-optimal accuracy under given fairness levels. Extensive experiments on multiple datasets across various data heterogeneity demonstrate that FedFACT consistently outperforms baselines in balancing accuracy and global-local fairness.