A Novel Optimized Asynchronous Federated Learning Framework
This addresses communication inefficiencies in federated learning for applications like credit assessment and medical fields, representing an incremental improvement.
The paper tackled the communication bottleneck in Asynchronous Federated Learning by proposing the VAFL framework, which reduced communication times by 51.02% with a 48.23% average compression rate and enabled faster model convergence.
Federated Learning (FL) since proposed has been applied in many fields, such as credit assessment, medical, etc. Because of the difference in the network or computing resource, the clients may not update their gradients at the same time that may take a lot of time to wait or idle. That's why Asynchronous Federated Learning (AFL) method is needed. The main bottleneck in AFL is communication. How to find a balance between the model performance and the communication cost is a challenge in AFL. This paper proposed a novel AFL framework VAFL. And we verified the performance of the algorithm through sufficient experiments. The experiments show that VAFL can reduce the communication times about 51.02\% with 48.23\% average communication compression rate and allow the model to be converged faster. The code is available at \url{https://github.com/RobAI-Lab/VAFL}