Federated Learning beyond the Star: Local D2D Model Consensus with Global Cluster Sampling

Frank Po Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi

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

3 Scopus citations

Abstract

Federated learning has emerged as a popular technique for distributing model training across the network edge. Its learning architecture is conventionally a star topology be-tween the devices and a central server. In this paper, we propose two timescale hybrid federated learning (TT-Hf), which migrates to a more distributed topology via device-to-device (D2D) communications. In TT-HF, local model training occurs at devices via successive gradient iterations, and the synchronization process occurs at two timescales: (i) macro-scale, where global aggregations are carried out via device-server interactions, and (ii) micro-scale, where local aggregations are carried out via D2D cooperative consensus formation in different device clusters. Our theoretical analysis reveals how device, cluster, and network-level parameters affect the convergence of TT-HF, and leads to a set of conditions under which a convergence rate of O(1/t) is guaranteed. Experimental results demonstrate the improvements in convergence and utilization that can be obtained by TT-HF over state-of-the-art federated learning baselines.

Original languageEnglish (US)
Title of host publication2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728181042
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE Global Communications Conference, GLOBECOM 2021 - Madrid, Spain
Duration: Dec 7 2021Dec 11 2021

Publication series

Name2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings

Conference

Conference2021 IEEE Global Communications Conference, GLOBECOM 2021
Country/TerritorySpain
CityMadrid
Period12/7/2112/11/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Health Informatics

Fingerprint

Dive into the research topics of 'Federated Learning beyond the Star: Local D2D Model Consensus with Global Cluster Sampling'. Together they form a unique fingerprint.

Cite this