文献类型：期刊文献

英文题名：Federated learning on non-IID data: A survey

作者：Zhu, Hangyu[1];Xu, Jinjin[2];Liu, Shiqing[1];Jin, Yaochu[1]

机构：[1]Univ Surrey, Dept Comp Sci, Guildford GU2 7XH, Surrey, England;[2]East China Univ Sci Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2021

卷号：465

起止页码：371

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20210137418);WOS:【SCI-EXPANDED(收录号:WOS:000704376900007)】；

语种：英文

外文关键词：Federated learning; Machine learning; Non-IID data; Privacy preservation

摘要：Federated learning is an emerging distributed machine learning framework for privacy preservation. However, models trained in federated learning usually have worse performance than those trained in the standard centralized learning mode, especially when the training data are not independent and identically distributed (Non-IID) on the local devices. In this survey, we provide a detailed analysis of the influence of Non-IID data on both parametric and non-parametric machine learning models in both horizontal and vertical federated learning. In addition, current research work on handling challenges of NonIID data in federated learning are reviewed, and both advantages and disadvantages of these approaches are discussed. Finally, we suggest several future research directions before concluding the paper. (c) 2021 Elsevier B.V. All rights reserved.