Federating for Learning Group Fair Models
This work addresses fairness for demographic groups in federated learning, but it is incremental as it builds on existing federated fairness criteria.
The paper tackled the problem of ensuring minmax group fairness in federated learning when participants have access to different population groups, and it proposed the FedMinMax algorithm, which experimentally improved group fairness in various setups.
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.