PraFFL: A Preference-Aware Scheme in Fair Federated Learning

arXiv:2404.08973v1 Announce Type: new
Abstract: Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model for any special group (e.g., male or female) of sensitive features. However, there is a trade-off between model performance and fairness, i.e., improving fairness will decrease model performance. Existing approaches have characterized such a trade-off by introducing hyperparameters to quantify client's preferences for fairness and model performance. Nevertheless, these methods are limited to scenarios where each client has only …

abstract arxiv cs.cy cs.dc cs.lg fair fairness features federated learning however improving performance trade trade-off type unbiased will