Generalizing to Unseen Domains: A Survey on Domain Generalization

doi:10.1109/TKDE.2022.3178128

	Generalizing to Unseen Domains: A Survey on Domain Generalization
	Wang, Jindong 1; Lan, Cuiling 1; Liu, Chang 1; Ouyang, Yidong 2; Qin, Tao 1; Lu, Wang 3; Chen, Yiqiang 3; Zeng, Wenjun 1; Yu, Philip S.4,5
	2023-08-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	35 期号:8 页码:8052-8072
摘要	Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future.
关键词	Domain generalization domain adaptation transfer learning out-of-distribution generalization
DOI	10.1109/TKDE.2022.3178128
收录类别	SCI
语种	英语
资助项目	NSFC[61972383] ; NSF[III-1763325] ; NSF[III-1909323] ; NSF[III-2106758] ; NSF[SaTC-1930941]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:001033571000032
出版者	IEEE COMPUTER SOC
引用统计	被引频次：352[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21326
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Jindong
作者单位	1.Microsoft Res Asia, Beijing 100080, Peoples R China 2.Chinese Univ Hong Kong, Sch Data Sci, Shenzhen 518172, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 4.Univ Illinois, Chicago, IL 60607 USA 5.Tsinghua Univ, Inst Data Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Jindong,Lan, Cuiling,Liu, Chang,et al. Generalizing to Unseen Domains: A Survey on Domain Generalization[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2023,35(8):8052-8072.
APA	Wang, Jindong.,Lan, Cuiling.,Liu, Chang.,Ouyang, Yidong.,Qin, Tao.,...&Yu, Philip S..(2023).Generalizing to Unseen Domains: A Survey on Domain Generalization.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,35(8),8052-8072.
MLA	Wang, Jindong,et al."Generalizing to Unseen Domains: A Survey on Domain Generalization".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 35.8(2023):8052-8072.