A Comprehensive Survey on Transfer Learning

doi:10.1109/JPROC.2020.3004555

	A Comprehensive Survey on Transfer Learning
	Zhuang, Fuzhen 2,3; Qi, Zhiyuan 2,3; Duan, Keyu 2,3; Xi, Dongbo 2,3; Zhu, Yongchun 2,3; Zhu, Hengshu 1; Xiong, Hui 4; He, Qing 2,3
刊名	PROCEEDINGS OF THE IEEE
	2021
卷号	109 期号:1 页码:43-76
关键词	Task analysis Semisupervised learning Data models Covariance matrices Machine learning Adaptation models Kernel Domain adaptation interpretation machine learning transfer learning
ISSN号	0018-9219
DOI	10.1109/JPROC.2020.3004555
英文摘要	Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target-domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. Due to the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Unlike previous surveys, this survey article reviews more than 40 representative transfer learning approaches, especially homogeneous transfer learning approaches, from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, over 20 representative transfer learning models are used for experiments. The models are performed on three different data sets, that is, Amazon Reviews, Reuters-21578, and Office-31, and the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.
资助项目	National Key Research and Development Program of China[2018YFB1004300] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[U1811461] ; National Natural Science Foundation of China[61773361] ; National Natural Science Foundation of China[61836013] ; Project of Youth Innovation Promotion Association CAS[2017146]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000600848500003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16587]
专题	中国科学院计算技术研究所
通讯作者	Zhuang, Fuzhen; Qi, Zhiyuan
作者单位	1.Baidu Inc, Beijing 100085, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Rutgers State Univ, Newark, NJ 08854 USA
推荐引用方式 GB/T 7714	Zhuang, Fuzhen,Qi, Zhiyuan,Duan, Keyu,et al. A Comprehensive Survey on Transfer Learning[J]. PROCEEDINGS OF THE IEEE,2021,109(1):43-76.
APA	Zhuang, Fuzhen.,Qi, Zhiyuan.,Duan, Keyu.,Xi, Dongbo.,Zhu, Yongchun.,...&He, Qing.(2021).A Comprehensive Survey on Transfer Learning.PROCEEDINGS OF THE IEEE,109(1),43-76.
MLA	Zhuang, Fuzhen,et al."A Comprehensive Survey on Transfer Learning".PROCEEDINGS OF THE IEEE 109.1(2021):43-76.