A Review on Evolutionary Multitask Optimization: Trends and Challenges

Evolutionary algorithms (EAs) possess strong problem-solving abilities and have been applied in a wide range of applications. However, they still suffer from a high computational burden and poor generalization ability. To overcome the limitations, numerous studies consider conducting knowledge extra...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on evolutionary computation Vol. 26; no. 5; pp. 941 - 960
Main Authors: Wei, Tingyang, Wang, Shibin, Zhong, Jinghui, Liu, Dong, Zhang, Jun
Format: Journal Article
Language:English
Published: New York IEEE 01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:1089-778X, 1941-0026
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Evolutionary algorithms (EAs) possess strong problem-solving abilities and have been applied in a wide range of applications. However, they still suffer from a high computational burden and poor generalization ability. To overcome the limitations, numerous studies consider conducting knowledge extraction across distinct optimization task domains. Among these research strands, one representative tributary is evolutionary multitask optimization (EMTO) that aims to resolve multiple optimization tasks simultaneously. The underlying attribute of implicit parallelism for EAs can well incorporate with the framework of EMTO, giving rise to the ascending EMTO studies. This review is intended to present a detailed exposition on the research in the EMTO area. We reveal the core components for designing the EMTO algorithms. Subsequently, we organize the works lying in the fusions between EMTO and traditional EAs. By analyzing the associations for diverse strategies in different branches of EMTO, this review uncovers the research trends and the potentially important directions, with additional interesting real-world applications mentioned.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1089-778X
1941-0026
DOI:10.1109/TEVC.2021.3139437