Federated Learning

Click the Cite button above to import publication metadata into your reference management software. Abstract Biased gradient compression with error feedback (EF) reduces communication in federated learning (FL), but under non-IID data, the residual error can decay slowly, causing gradient mismatch and stalled progress in the early rounds.

Communication overhead and privacy risks remain significant challenges in federated learning (FL). We introduce Partial Model Sharing …

will be updated.