On the Convergence Rate of Federated Learning over Unreliable Networks

Chenyuan Feng, Howard H. Yang, Zihan Chen, Daquan Feng, Zhenzhong Wang, Tony Q.S. Quek

研究成果: Conference contribution

2 引文 斯高帕斯(Scopus)

摘要

Considering unreliable wireless networks, the efficiency of training a statistical model via Federated Learning (FL) over wireless networks is studied in this work. The system consists of a server and a swarm of end-user devices that are termed as clients. The server allots the statistical model directly onto the clients for local training, based on the dataset that resides on their devices, periodically collects the trained parameters to produce an improved model, and sends it back to the clients for a new round of local computing. This process repeats for multiple rounds until the global model converges. Due to unreliable wireless channels and limited communication resources, the server can only select a handful of clients for parameter updates at each iteration. Analytical expressions are derived to characterize the FL convergence rate by accounting for the transmission reliability and momentum method. The analyses unveil that in networks with reliable connections, model training can be accelerated by expanding the bandwidth to include more clients in each communication round, but it becomes ineffectual when the connections are unreliable. Moreover, it is also confirmed that adopting momentum in the global aggregation stage of FL improves the convergence rate, and such an approach is more insulated from the effects of communication failures. These theoretical findings are validated by extensive empirical simulations.

原文English
主出版物標題2021 Computing, Communications and IoT Applications, ComComAp 2021
發行者Institute of Electrical and Electronics Engineers Inc.
頁面59-64
頁數6
ISBN(電子)9781665427975
DOIs
出版狀態Published - 2021
事件2021 Computing, Communications and IoT Applications, ComComAp 2021 - Shenzhen, China
持續時間: 2021 11月 262021 11月 28

出版系列

名字2021 Computing, Communications and IoT Applications, ComComAp 2021

Conference

Conference2021 Computing, Communications and IoT Applications, ComComAp 2021
國家/地區China
城市Shenzhen
期間21-11-2621-11-28

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 資訊系統與管理
  • 能源工程與電力技術
  • 電氣與電子工程
  • 儀器

指紋

深入研究「On the Convergence Rate of Federated Learning over Unreliable Networks」主題。共同形成了獨特的指紋。

引用此