A Novel Optimized Asynchronous Federated Learning Framework

TL;DR

This paper introduces VAFL, a new asynchronous federated learning framework that significantly reduces communication costs and accelerates model convergence, addressing key challenges in federated learning environments.

Contribution

The paper presents VAFL, a novel asynchronous federated learning framework that balances communication efficiency and model performance, verified through extensive experiments.

Findings

VAFL reduces communication by 51.02%.

VAFL achieves a 48.23% communication compression rate.

VAFL enables faster model convergence.

Abstract

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}