<ul><li>Federated Learning (FL) faces performance issues with non-IID data due to local classifier bias.</li><li>UniVarFL is a novel FL framework that directly addresses these issues without global model dependency.</li><li>It leverages two regularization strategies during local training: Classifier Variance Regularization and Hyperspherical Uniformity Regularization.</li><li>Extensive experiments show UniVarFL outperforms existing methods in accuracy, making it a promising solution for real-world FL deployments.</li></ul>

UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data

Discover more