Federated Fairness without Access to Sensitive Groups
This addresses fairness challenges in federated settings where sensitive group definitions are unavailable, offering a practical solution for real-world applications with incremental improvements over existing methods.
The paper tackles the problem of ensuring group fairness in federated learning without requiring predefined sensitive groups or labels, proposing an approach that learns a Pareto efficient global model to guarantee worst-case group fairness with a trade-off between fairness and utility, achieving improved performance for the worst-performing group without significantly harming average performance.
Current approaches to group fairness in federated learning assume the existence of predefined and labeled sensitive groups during training. However, due to factors ranging from emerging regulations to dynamics and location-dependency of protected groups, this assumption may be unsuitable in many real-world scenarios. In this work, we propose a new approach to guarantee group fairness that does not rely on any predefined definition of sensitive groups or additional labels. Our objective allows the federation to learn a Pareto efficient global model ensuring worst-case group fairness and it enables, via a single hyper-parameter, trade-offs between fairness and utility, subject only to a group size constraint. This implies that any sufficiently large subset of the population is guaranteed to receive at least a minimum level of utility performance from the model. The proposed objective encompasses existing approaches as special cases, such as empirical risk minimization and subgroup robustness objectives from centralized machine learning. We provide an algorithm to solve this problem in federation that enjoys convergence and excess risk guarantees. Our empirical results indicate that the proposed approach can effectively improve the worst-performing group that may be present without unnecessarily hurting the average performance, exhibits superior or comparable performance to relevant baselines, and achieves a large set of solutions with different fairness-utility trade-offs.