Temel Kavramlar
ASYN2F is an effective asynchronous federated learning framework that outperforms existing techniques in terms of performance and convergence speed.
Özet
ASYN2F introduces bidirectional model aggregation, allowing for faster convergence and lower communication costs compared to other methods. The framework addresses the issue of obsolete information at workers, leading to improved model performance. Extensive experiments demonstrate the superiority of ASYN2F in various scenarios, making it a practical solution for real-world deployment.
İstatistikler
ASYN2F achieves 92.86% accuracy with fixed LR=0.01 on overlapping iid sub-datasets.
Synchronously-decayed LR setting results in 95.48% accuracy for ASYN2F on overlapping iid sub-datasets.
ASYN2F converges faster than M-Step KAFL and FedAvg in all experimental scenarios.