Federating for Learning Group Fair Models
arXiv:2110.01999
Abstract
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness in paradigms where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how this 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 methods in terms of group fairness in various federated learning setups.
References in corpus (7)
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Strategies for Improving Communication Efficiency
- Equality of Opportunity in Supervised Learning
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Minimax Pareto Fairness: A Multi Objective Perspective
- Federated Learning Meets Multi-objective Optimization
- Distributionally Robust Federated Averaging