Minimax Demographic Group Fairness in Federated Learning

Conference Paper

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how our proposed group fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm - FedMinMax - for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or superior performance.

Full Text

Duke Authors

Cited Authors

  • Papadaki, A; Martinez, N; Bertran, M; Sapiro, G; Rodrigues, M

Published Date

  • June 21, 2022

Published In

  • Acm International Conference Proceeding Series

Start / End Page

  • 142 - 159

International Standard Book Number 13 (ISBN-13)

  • 9781450393522

Digital Object Identifier (DOI)

  • 10.1145/3531146.3533081

Citation Source

  • Scopus