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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publication2021 Computing, Communications and IoT Applications, ComComAp 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages59-64
Number of pages6
ISBN (Electronic)9781665427975
DOIs
Publication statusPublished - 2021
Event2021 Computing, Communications and IoT Applications, ComComAp 2021 - Shenzhen, China
Duration: 2021 Nov 262021 Nov 28

Publication series

Name2021 Computing, Communications and IoT Applications, ComComAp 2021

Conference

Conference2021 Computing, Communications and IoT Applications, ComComAp 2021
Country/TerritoryChina
CityShenzhen
Period21-11-2621-11-28

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems and Management
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'On the Convergence Rate of Federated Learning over Unreliable Networks'. Together they form a unique fingerprint.

Cite this