Skip to yearly menu bar Skip to main content


Poster

Fair Federated Learning via the Proportional Veto Core

Bhaskar Ray Chaudhury · Aniket Murhekar · Zhuowen Yuan · Bo Li · Ruta Mehta · Ariel Procaccia

Hall C 4-9 #2317
[ ] [ Paper PDF ]
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Previous work on fairness in federated learning introduced the notion of core stability, which provides utility-based fairness guarantees to any subset of participating agents. However, these guarantees require strong assumptions on agent utilities that render them impractical. To address this shortcoming, we measure the quality of output models in terms of their ordinal rank instead of their cardinal utility, and use this insight to adapt the classical notion of proportional veto core (PVC) from social choice theory to the federated learning setting. We prove that models that are PVC-stable exist in very general learning paradigms, even allowing non-convex model sets, as well as non-convex and non-concave loss functions. We also design Rank-Core-Fed, a distributed federated learning algorithm, to train a PVC-stable model. Finally, we demonstrate that Rank-Core-Fed outperforms baselines in terms of fairness on different datasets.

Chat is not available.