FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
By: Li Zhang , Zhongxuan Han , Chaochao chen and more
Potential Business Impact:
Makes AI fair for everyone, not just some.
With 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 pose two fundamental, unresolved challenges for fair FL: (i) Harmonizing global and local fairness in multi-class classification; (ii) Enabling a controllable, optimal accuracy-fairness trade-off. To tackle the aforementioned 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 in multi-class case, yielding models with minimal performance decline while guaranteeing fairness. To effectively realize an adjustable, optimal accuracy-fairness balance, we derive specific characterizations of the Bayes-optimal fair classifiers for reformulating fair FL as personalized cost-sensitive learning problem for in-processing, and 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.
Similar Papers
pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning
Machine Learning (CS)
Makes AI fair for everyone, not just some.
GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks
Machine Learning (CS)
Protects AI learning from sneaky data tricks.
LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning
Machine Learning (CS)
Makes AI fair for everyone, everywhere.