FedDisco: Federated Learning with Discrepancy-Aware Collaboration

1 code implementation • 30 May 2023 • Rui Ye, Mingkai Xu, Jianyu Wang, Chenxin Xu, Siheng Chen, Yanfeng Wang

However, based on our empirical observations and theoretical analysis, we find that the dataset size is not optimal and the discrepancy between local and global category distributions could be a beneficial and complementary indicator for determining aggregation weights.

Federated Learning