The Cost of Local and Global Fairness in Federated Learning
This work addresses fairness in federated learning for applications like finance and healthcare, but it is incremental as it builds on prior frameworks by combining global and local fairness in multi-class settings.
This paper tackles the problem of enforcing both global and local fairness in multi-class federated learning, proposing a framework that minimizes accuracy loss while achieving specified fairness levels, with experimental results showing it outperforms current state-of-the-art methods in accuracy-fairness trade-offs and reduces computational and communication costs.
With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of fairness are important in FL: global and local fairness. Global fairness addresses the disparity across the entire population and local fairness is concerned with the disparity within each client. Prior fair FL frameworks have improved either global or local fairness without considering both. Furthermore, while the majority of studies on fair FL focuses on binary settings, many real-world applications are multi-class problems. This paper proposes a framework that investigates the minimum accuracy lost for enforcing a specified level of global and local fairness in multi-class FL settings. Our framework leads to a simple post-processing algorithm that derives fair outcome predictors from the Bayesian optimal score functions. Experimental results show that our algorithm outperforms the current state of the art (SOTA) with regard to the accuracy-fairness tradoffs, computational and communication costs. Codes are available at: https://github.com/papersubmission678/The-cost-of-local-and-global-fairness-in-FL .