Federated Learning With Non-IID Data: A Survey
IEEE Internet of Things Journal · 01.06.2024 · 11 (11) · 19188-19209
DOI: 10.1109/jiot.2024.3376548 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2024. Verfasst von Zili Lu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 474-mal zitiert (Crossref) und nennt 117 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Pre-Research Project of Songshan Laboratory, Key Research Project for Higher Education of Henan Province.
Abstract (Originalsprache)
Federated learning (FL) is an efficient decentralized machine learning methodology for processing nonindependent and identically distributed (non-IID) data due to geographical and temporal distribution differences. Non-IID data generally indicates substantial disparities in data distribution and features among clients. This assumption is completely different from the conventional assumption of independent and identically distributed (IID) data in which all clients’ data originates from the same distribution. There are many factors that affect the features of non-IID data, such as user preferences, data collection methods, and client characteristics. The factors of data distribution, category proportions, and feature representation also affect the statistical properties of non-IID data. This article conducts an in-depth exploration of FL with the consideration of diverse features and statistical properties of non-IID data. Specifically, we first discuss the impact of non-IID data on communication efficiency, model convergence, and FL accuracy. The presence of non-IID data leads to increased communication overhead, imbalanced class distribution, and uneven local model updates. All of these affect FL convergence and performance. Then, we present the latest advanced techniques, such as data partitioning/sharing, client selection, differential privacy, and secure aggregation, which are used to address the challenges posed by non-IID data in terms of communication efficiency and privacy protection. Furthermore, we show the emerging applications and use cases of FL with non-IID data in various domains, such as healthcare, Internet of Things, and edge computing. Overall, this survey provides a comprehensive understanding of FL with non-IID data, including the challenges, advancements, and practical applications in different areas.
Förderung
- National Natural Science Foundation of China
- Pre-Research Project of Songshan Laboratory
- Key Research Project for Higher Education of Henan Province
- EU Horizon 2020 Research and Innovation Programme under the Marie Skłodowska-Curie Grant
Zitieren
APA
Lu, Z., Pan, H., Dai, Y., Si, X., & Zhang, Y. (2024). Federated Learning With Non-IID Data: A Survey. IEEE Internet of Things Journal, 11(11), 19188-19209. https://doi.org/10.1109/jiot.2024.3376548
Vancouver
Lu Z, Pan H, Dai Y, Si X, Zhang Y. Federated Learning With Non-IID Data: A Survey. IEEE Internet of Things Journal. 2024;11(11):19188-19209. doi:10.1109/jiot.2024.3376548
BibTeX
@article{Lu2024,
author = {Lu, Zili and Pan, Heng and Dai, Yueyue and Si, Xueming and Zhang, Yan},
title = {Federated Learning With Non-IID Data: A Survey},
journal = {IEEE Internet of Things Journal},
year = {2024},
volume = {11},
number = {11},
pages = {19188--19209},
doi = {10.1109/jiot.2024.3376548}
}
EUVIMED