articleIEEE Internet of Things JournalMar 18, 2024Closed access

Federated Learning With Non-IID Data: A Survey

ZLZili LuHPHeng PanYDYueyue DaiXSXueming SiYZYan Zhang

Zhongyuan University of Technology · Huazhong University of Science and Technology · +1 more institution

Indexed incrossref

Abstract

Federated learning (FL) is an efficient decentralized machine learning methodology for processing non-independent 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…

Citation impact

289
total citations
FWCI
90.94
Percentile
100%
References
117
Citations per year

Authors

5

Topics & keywords

Topics
Keywords
  • Computer science
  • Data modeling
  • Database
No related works found for this paper.

Funding