Generalizing to Unseen Domains: A Survey on Domain Generalization

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 interest...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering Vol. 35; no. 8; pp. 8052 - 8072
Main Authors: Wang, Jindong, Lan, Cuiling, Liu, Chang, Ouyang, Yidong, Qin, Tao, Lu, Wang, Chen, Yiqiang, Zeng, Wenjun, Yu, Philip S.
Format: Journal Article
Language:English
Published: New York IEEE 01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adaptation models
Algorithms
Computational modeling
Data models
domain adaptation
Domain generalization
Machine learning
Multitasking
out-of-distribution generalization
Predictive models
Task analysis
Training
transfer learning
ISSN:1041-4347, 1558-2191
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2022.3178128