Federated Fairness without Access to Sensitive Groups

arXiv:2402.14929v1 Announce Type: new
Abstract: 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 …

abstract arxiv cs.ai cs.cy cs.dc cs.lg current dynamics fairness federated learning location regulations training type work world