Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout

no code implementations • 11 Mar 2023 • Jian Xu, Meiling Yang, Wenbo Ding, Shao-Lun Huang

The label distribution skew induced data heterogeniety has been shown to be a significant obstacle that limits the model performance in federated learning, which is particularly developed for collaborative model training over decentralized data sources while preserving user privacy.

Federated Learning