Evolutionary multitasking via explicit autoencoding

Evolutionary multitasking (EMT) is an emerging research topic in the field of evolutionary computation. In contrast to the traditional single-task evolutionary search, EMT conducts evolutionary search on multiple tasks simultaneously. It aims to improve convergence characteristics across multiple op...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng, Liang, Zhou, Lei, Zhong, Jinghui, Gupta, Abhishek, Ong, Yew-Soon, Tan, Kay-Chen, Qin, A. K.
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/139920
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-139920
record_format dspace
spelling sg-ntu-dr.10356-1399202020-05-22T08:28:58Z Evolutionary multitasking via explicit autoencoding Feng, Liang Zhou, Lei Zhong, Jinghui Gupta, Abhishek Ong, Yew-Soon Tan, Kay-Chen Qin, A. K. School of Computer Science and Engineering Engineering::Computer science and engineering Autoencoder Evolutionary Optimization Evolutionary multitasking (EMT) is an emerging research topic in the field of evolutionary computation. In contrast to the traditional single-task evolutionary search, EMT conducts evolutionary search on multiple tasks simultaneously. It aims to improve convergence characteristics across multiple optimization problems at once by seamlessly transferring knowledge among them. Due to the efficacy of EMT, it has attracted lots of research attentions and several EMT algorithms have been proposed in the literature. However, existing EMT algorithms are usually based on a common mode of knowledge transfer in the form of implicit genetic transfer through chromosomal crossover. This mode cannot make use of multiple biases embedded in different evolutionary search operators, which could give better search performance when properly harnessed. Keeping this in mind, this paper proposes an EMT algorithm with explicit genetic transfer across tasks, namely EMT via autoencoding, which allows the incorporation of multiple search mechanisms with different biases in the EMT paradigm. To confirm the efficacy of the proposed EMT algorithm with explicit autoencoding, comprehensive empirical studies have been conducted on both the singleand multi-objective multitask optimization problems. 2020-05-22T08:28:58Z 2020-05-22T08:28:58Z 2018 Journal Article Feng, L., Zhou, L., Zhong, J., Gupta, A., Ong, Y.-S., Tan, K.-C., & Qin, A. K. (2019). Evolutionary multitasking via explicit autoencoding. IEEE Transactions on Cybernetics, 49(9), 3457-3470. doi:10.1109/TCYB.2018.2845361 2168-2267 https://hdl.handle.net/10356/139920 10.1109/TCYB.2018.2845361 29994415 2-s2.0-85049311892 9 49 3457 3470 en IEEE Transactions on Cybernetics © 2018 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Autoencoder
Evolutionary Optimization
spellingShingle Engineering::Computer science and engineering
Autoencoder
Evolutionary Optimization
Feng, Liang
Zhou, Lei
Zhong, Jinghui
Gupta, Abhishek
Ong, Yew-Soon
Tan, Kay-Chen
Qin, A. K.
Evolutionary multitasking via explicit autoencoding
description Evolutionary multitasking (EMT) is an emerging research topic in the field of evolutionary computation. In contrast to the traditional single-task evolutionary search, EMT conducts evolutionary search on multiple tasks simultaneously. It aims to improve convergence characteristics across multiple optimization problems at once by seamlessly transferring knowledge among them. Due to the efficacy of EMT, it has attracted lots of research attentions and several EMT algorithms have been proposed in the literature. However, existing EMT algorithms are usually based on a common mode of knowledge transfer in the form of implicit genetic transfer through chromosomal crossover. This mode cannot make use of multiple biases embedded in different evolutionary search operators, which could give better search performance when properly harnessed. Keeping this in mind, this paper proposes an EMT algorithm with explicit genetic transfer across tasks, namely EMT via autoencoding, which allows the incorporation of multiple search mechanisms with different biases in the EMT paradigm. To confirm the efficacy of the proposed EMT algorithm with explicit autoencoding, comprehensive empirical studies have been conducted on both the singleand multi-objective multitask optimization problems.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Feng, Liang
Zhou, Lei
Zhong, Jinghui
Gupta, Abhishek
Ong, Yew-Soon
Tan, Kay-Chen
Qin, A. K.
format Article
author Feng, Liang
Zhou, Lei
Zhong, Jinghui
Gupta, Abhishek
Ong, Yew-Soon
Tan, Kay-Chen
Qin, A. K.
author_sort Feng, Liang
title Evolutionary multitasking via explicit autoencoding
title_short Evolutionary multitasking via explicit autoencoding
title_full Evolutionary multitasking via explicit autoencoding
title_fullStr Evolutionary multitasking via explicit autoencoding
title_full_unstemmed Evolutionary multitasking via explicit autoencoding
title_sort evolutionary multitasking via explicit autoencoding
publishDate 2020
url https://hdl.handle.net/10356/139920
_version_ 1681058702723907584