Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering
This work addresses the challenge of aligning local fairness with accuracy in Federated Learning for distributed and heterogeneous data environments, representing an incremental improvement over existing personalized and fair FL methods.
The paper tackles the problem of low local accuracy and fairness in Federated Learning under heterogeneous settings by proposing clustering-based algorithms that balance local accuracy and fairness without explicit fairness intervention, achieving performance that matches or exceeds existing locally fair FL approaches.
Federated Learning (FL) has been a pivotal paradigm for collaborative training of machine learning models across distributed datasets. In heterogeneous settings, it has been observed that a single shared FL model can lead to low local accuracy, motivating personalized FL algorithms. In parallel, fair FL algorithms have been proposed to enforce group fairness on the global models. Again, in heterogeneous settings, global and local fairness do not necessarily align, motivating the recent literature on locally fair FL. In this paper, we propose new FL algorithms for heterogeneous settings, spanning the space between personalized and locally fair FL. Building on existing clustering-based personalized FL methods, we incorporate a new fairness metric into cluster assignment, enabling a tunable balance between local accuracy and fairness. Our methods match or exceed the performance of existing locally fair FL approaches, without explicit fairness intervention. We further demonstrate (numerically and analytically) that personalization alone can improve local fairness and that our methods exploit this alignment when present.