GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning
This addresses fairness issues in federated learning for applications like image and text processing, though it is incremental as it builds on existing regularization methods.
The paper tackles the problem of ensuring both group and individual fairness in federated learning by proposing the GIFAIR-FL framework, which uses a regularization term to penalize loss disparities across client groups, resulting in improved fairness metrics while maintaining competitive accuracy in image classification and text prediction tasks.
In this paper we propose \texttt{GIFAIR-FL}: a framework that imposes \textbf{G}roup and \textbf{I}ndividual \textbf{FAIR}ness to \textbf{F}ederated \textbf{L}earning settings. By adding a regularization term, our algorithm penalizes the spread in the loss of client groups to drive the optimizer to fair solutions. Our framework \texttt{GIFAIR-FL} can accommodate both global and personalized settings. Theoretically, we show convergence in non-convex and strongly convex settings. Our convergence guarantees hold for both $i.i.d.$ and non-$i.i.d.$ data. To demonstrate the empirical performance of our algorithm, we apply our method to image classification and text prediction tasks. Compared to existing algorithms, our method shows improved fairness results while retaining superior or similar prediction accuracy.