arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.09487cs.LGcs.DC
收藏

一种新的优化异步联邦学习框架

A Novel Optimized Asynchronous Federated Learning Framework

Hainan University(海南大学);Hainan Blockchain Technology Engineering Research Center(海南区块链技术工程研究中心)

Zhicheng Zhou, Hailong Chen, Kunhua Li, Fei Hu, Bingjie Yan, Jieren Cheng, Xuyan Wei, Bernie Liu, Xiulai Li, Fuwen Chen, Yongji Sui

摘要:

联邦学习(Federated Learning,FL)自提出以来,已经在信用评估、医疗等领域得到了广泛的应用。由于网络或计算资源的差异,客户端可能不会同时更新其梯度,这可能需要花费大量的时间等待或空闲。这就是为什么需要异步联邦学习(AFL)方法。劳联的主要瓶颈是通讯。如何在模型性能和通信代价之间找到一个平衡点是AFL面临的一个挑战。提出了一种新的AFL框架VAFL。并通过大量实验验证了算法的性能。实验结果表明,VAFL在平均通信压缩率为48.23%的情况下,可减少通信次数约51.02%,并能使模型更快地收敛。代码可在\url{https://github.com/RobAI-Lab/VAFL}上获得

英文摘要:

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}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑