AIBullisharXiv – CS AI · 15h ago6/10
🧠
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
Researchers propose PushCen-ADFL, a new framework for asynchronous decentralized federated learning that reduces communication overhead by over 80% while improving accuracy under data heterogeneity. The approach uses centroid-based message compression and bias-correction aggregation to enable stable model training across distributed systems without central coordination.