Distribution-Regularized Federated Learning on Non-IID Data

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

11 Scopus Citations
View graph of relations

Author(s)

  • Yansheng Wang
  • Yongxin Tong
  • Ruisheng Zhang
  • Sinno Jialin Pan
  • Lixin Fan
  • Qiang Yang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE 39th International Conference on Data Engineering (ICDE 2023)
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages2113-2125
ISBN (electronic)979-8-3503-2227-9
Publication statusPublished - 2023

Publication series

NameProceedings - International Conference on Data Engineering
Volume2023-April
ISSN (Print)1084-4627

Conference

Title39th IEEE International Conference on Data Engineering (ICDE 2023)
LocationMarriott Anaheim
PlaceUnited States
CityAnaheim
Period3 - 7 April 2023

Abstract

Federated learning (FL) has emerged as a popular machine learning paradigm recently. Compared with traditional distributed learning, its unique challenges mainly lie in communication efficiency and non-IID (heterogeneous data) problem. While the widely adopted framework FedAvg can reduce communication overhead significantly, its effectiveness on non-IID data still lacks exploration. In this paper, we study the non-IID problem of FL from the perspective of domain adaptation. We propose a distribution regularization for FL on non-IID data such that the discrepancy of data distributions between clients is reduced. To further reduce the communication cost, we devise two novel distributed learning algorithms, namely rFedAvg and rFedAvg+, for efficiently learning with the distribution regularization. More importantly, we theoretically establish their convergence for strongly convex objectives. Extensive experiments on 4 datasets with both CNN and LSTM as learning models verify the effectiveness and efficiency of the proposed algorithms. © 2023 IEEE.

Citation Format(s)

Distribution-Regularized Federated Learning on Non-IID Data. / Wang, Yansheng; Tong, Yongxin; Zhou, Zimu et al.
Proceedings - 2023 IEEE 39th International Conference on Data Engineering (ICDE 2023). Institute of Electrical and Electronics Engineers, Inc., 2023. p. 2113-2125 (Proceedings - International Conference on Data Engineering; Vol. 2023-April).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review