FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning Article Swipe

MAKE IMPACT

Li Zhang , Zhongxuan Han , C. L. Philip Chen , Xiaohua Feng , Jiaming Zhang , Yuyuan Li · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2506.03777

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.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2506.03777

PDF

https://arxiv.org/pdf/2506.03777

OA Status

green

OpenAlex ID

https://openalex.org/W4416073756

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416073756

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2506.03777

Digital Object Identifier

Title

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-06-04

Full publication date if available

Authors

Li Zhang, Zhongxuan Han, C. L. Philip Chen, Xiaohua Feng, Jiaming Zhang, Yuyuan Li

List of authors in order

Landing page

https://arxiv.org/abs/2506.03777

Publisher landing page

PDF URL

https://arxiv.org/pdf/2506.03777

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2506.03777

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload