Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data

Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

Federated edge learning (FEEL) has emerged as an effective approach to reduce the large communication latency in Cloud-based machine learning solutions, while preserving data privacy. Unfortunately, the learning performance of FEEL may be compromised due to limited training data in a single edge cluster. In this paper, we investigate a novel framework of FEEL, namely semi-decentralized federated edge learning (SD-FEEL). By allowing model aggregation across different edge clusters, SD-FEEL enjoys the benefit of FEEL in reducing the training latency, while improving the learning performance by accessing richer training data from multiple edge clusters. A training algorithm for SD-FEEL with three main procedures in each round is presented, including local model updates, intra-cluster and inter-cluster model aggregations, which is proved to converge on non-independent and identically distributed (non-IID) data. We also characterize the interplay between the network topology of the edge servers and the communication overhead of inter-cluster model aggregation on the training performance. Experiment results corroborate our analysis and demonstrate the effectiveness of SD-FFEL in achieving faster convergence than traditional federated learning architectures. Besides, guidelines on choosing critical hyper-parameters of the training algorithm are also provided.

Original languageEnglish
Title of host publication2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1898-1903
Number of pages6
ISBN (Electronic)9781665442664
DOIs
Publication statusPublished - Apr 2022
Event2022 IEEE Wireless Communications and Networking Conference, WCNC 2022 - Austin, United States
Duration: 10 Apr 202213 Apr 2022

Publication series

NameIEEE Wireless Communications and Networking Conference, WCNC
Volume2022-April
ISSN (Print)1525-3511

Conference

Conference2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
Country/TerritoryUnited States
CityAustin
Period10/04/2213/04/22

Keywords

  • communication efficiency
  • distributed machine learning
  • Federated learning
  • non-IID data

ASJC Scopus subject areas

  • Engineering(all)

Cite this