Heterogeneous Federated Learning: State-of-the-art and Research Challenges
ACM Computing Surveys · 31.03.2024 · 56 (3) · 1-44
DOI: 10.1145/3625558 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 21.10.2023. Verfasst von Mang Ye und 4 weiteren Autor:innen. Die Arbeit wurde bisher 619-mal zitiert (Crossref) und nennt 259 Literaturangaben.
Abstract (Originalsprache)
Federated learning (FL) has drawn increasing attention owing to its potential use in large-scale industrial applications. Existing FL works mainly focus on model homogeneous settings. However, practical FL typically faces the heterogeneity of data distributions, model architectures, network environments, and hardware devices among participant clients. Heterogeneous Federated Learning (HFL) is much more challenging, and corresponding solutions are diverse and complex. Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential. In this survey, we firstly summarize the various research challenges in HFL from five aspects: statistical heterogeneity, model heterogeneity, communication heterogeneity, device heterogeneity, and additional challenges. In addition, recent advances in HFL are reviewed and a new taxonomy of existing HFL methods is proposed with an in-depth analysis of their pros and cons. We classify existing methods from three different levels according to the HFL procedure: data-level, model-level, and server-level. Finally, several critical and promising future research directions in HFL are discussed, which may facilitate further developments in this field. A periodically updated collection on HFL is available at https://github.com/marswhu/HFL_Survey.
Zitieren
APA
Ye, M., Fang, X., Du, B., Yuen, P. C., & Tao, D. (2024). Heterogeneous Federated Learning: State-of-the-art and Research Challenges. ACM Computing Surveys, 56(3), 1-44. https://doi.org/10.1145/3625558
Vancouver
Ye M, Fang X, Du B, Yuen PC, Tao D. Heterogeneous Federated Learning: State-of-the-art and Research Challenges. ACM Computing Surveys. 2024;56(3):1-44. doi:10.1145/3625558
BibTeX
@article{Ye2024,
author = {Ye, Mang and Fang, Xiuwen and Du, Bo and Yuen, Pong C. and Tao, Dacheng},
title = {Heterogeneous Federated Learning: State-of-the-art and Research Challenges},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {3},
pages = {1--44},
doi = {10.1145/3625558}
}
EUVIMED