<ul data-eligibleForWebStory="true"><li>Federated Learning (FL) focuses on collaborative model training without sharing private data but faces fairness concerns due to biases in clients' datasets.</li><li>Heterogeneous data distributions across clients can lead to unfair models impacting different clients differently.</li><li>FeDa4Fair introduces a library to generate datasets and benchmarks for evaluating fairness in FL methods at global and client levels.</li><li>The paper aims to support more robust fairness research by facilitating consistent benchmarking and evaluating fairness outcomes for diverse clients.</li></ul>

FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation

Discover more