An Effective Ensemble Framework for Multi-Objective Optimization

Wenjun Wang, Shaoqiang Yang, Qiuzhen Lin (Corresponding Author), Qingfu Zhang, Ka Chun Wong, Carlos A.Coello Coello, Jianyong Chen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper proposes an effective ensemble framework for tackling multi-objective optimization problems, by combining the advantages of various evolutionary operators and selection criteria that are run on multiple populations. A simple ensemble algorithm is realized as a prototype to demonstrate our proposed framework. Two mechanisms, namely competition and cooperation, are employed to drive the running of the ensembles. Competition is designed by adaptively running different evolutionary operators on multiple populations. The operator that better fits the problem’s characteristics will receive more computational resources, being rewarded by a decomposition-based credit assignment strategy. Cooperation is achieved by a cooperative selection of the offspring generated by different populations. In this way, the promising offspring from one population have chances to migrate into the other populations to enhance their convergence or diversity. Moreover, the population update information is further exploited to build an evolutionary potentiality model, which is used to guide the evolutionary process. Our experimental results show the superior performance of our proposed ensemble algorithms in solving most cases of a set of thirty-one test problems, which corroborates the advantages of our ensemble framework.

Original languageEnglish
Article number8519635
Pages (from-to)645-659
Number of pages15
JournalIEEE Transactions on Evolutionary Computation
Volume23
Issue number4
Early online date1 Nov 2018
DOIs
Publication statusPublished - Aug 2019

Fingerprint

Multiobjective optimization
Multi-objective Optimization
Ensemble
Decomposition
Operator
Multiobjective Optimization Problems
Test Problems
Framework
Assignment
Update
Prototype
Decompose
Resources
Experimental Results
Demonstrate

Keywords

  • competitive evolution
  • cooperative selection.
  • ensemble framework
  • multi-objective optimization
  • multiobjective optimization
  • cooperative selection
  • Competitive evolution
  • ensemble framework (EF)

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Wang, W., Yang, S., Lin, Q., Zhang, Q., Wong, K. C., Coello, C. A. C., & Chen, J. (2019). An Effective Ensemble Framework for Multi-Objective Optimization. IEEE Transactions on Evolutionary Computation, 23(4), 645-659. [8519635]. https://doi.org/10.1109/TEVC.2018.2879078

An Effective Ensemble Framework for Multi-Objective Optimization. / Wang, Wenjun; Yang, Shaoqiang; Lin, Qiuzhen (Corresponding Author); Zhang, Qingfu; Wong, Ka Chun; Coello, Carlos A.Coello; Chen, Jianyong.

In: IEEE Transactions on Evolutionary Computation, Vol. 23, No. 4, 8519635, 08.2019, p. 645-659.

Research output: Contribution to journalArticle

Wang, W, Yang, S, Lin, Q, Zhang, Q, Wong, KC, Coello, CAC & Chen, J 2019, 'An Effective Ensemble Framework for Multi-Objective Optimization' IEEE Transactions on Evolutionary Computation, vol. 23, no. 4, 8519635, pp. 645-659. https://doi.org/10.1109/TEVC.2018.2879078
Wang, Wenjun ; Yang, Shaoqiang ; Lin, Qiuzhen ; Zhang, Qingfu ; Wong, Ka Chun ; Coello, Carlos A.Coello ; Chen, Jianyong. / An Effective Ensemble Framework for Multi-Objective Optimization. In: IEEE Transactions on Evolutionary Computation. 2019 ; Vol. 23, No. 4. pp. 645-659.
@article{612a6c4beba94baf957421053a604038,
title = "An Effective Ensemble Framework for Multi-Objective Optimization",
abstract = "This paper proposes an effective ensemble framework for tackling multi-objective optimization problems, by combining the advantages of various evolutionary operators and selection criteria that are run on multiple populations. A simple ensemble algorithm is realized as a prototype to demonstrate our proposed framework. Two mechanisms, namely competition and cooperation, are employed to drive the running of the ensembles. Competition is designed by adaptively running different evolutionary operators on multiple populations. The operator that better fits the problem’s characteristics will receive more computational resources, being rewarded by a decomposition-based credit assignment strategy. Cooperation is achieved by a cooperative selection of the offspring generated by different populations. In this way, the promising offspring from one population have chances to migrate into the other populations to enhance their convergence or diversity. Moreover, the population update information is further exploited to build an evolutionary potentiality model, which is used to guide the evolutionary process. Our experimental results show the superior performance of our proposed ensemble algorithms in solving most cases of a set of thirty-one test problems, which corroborates the advantages of our ensemble framework.",
keywords = "competitive evolution, cooperative selection., ensemble framework, multi-objective optimization, multiobjective optimization, cooperative selection, Competitive evolution, ensemble framework (EF)",
author = "Wenjun Wang and Shaoqiang Yang and Qiuzhen Lin and Qingfu Zhang and Wong, {Ka Chun} and Coello, {Carlos A.Coello} and Jianyong Chen",
note = "This work was supported by the National Natural Science Foundation of China under Grants 61876110, 61876163, and 61836005, a grant from ANR/RGC Joint Research Scheme sponsored by the Research Grants Council of the Hong Kong Special Administrative Region, China and France National Research Agency (Project No. A-CityU101/16), the Joint Funds of the National Natural Science Foundation of China under Key Program Grant U1713212, and CONACyT grant no. 221551.",
year = "2019",
month = "8",
doi = "10.1109/TEVC.2018.2879078",
language = "English",
volume = "23",
pages = "645--659",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1089-778X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - An Effective Ensemble Framework for Multi-Objective Optimization

AU - Wang, Wenjun

AU - Yang, Shaoqiang

AU - Lin, Qiuzhen

AU - Zhang, Qingfu

AU - Wong, Ka Chun

AU - Coello, Carlos A.Coello

AU - Chen, Jianyong

N1 - This work was supported by the National Natural Science Foundation of China under Grants 61876110, 61876163, and 61836005, a grant from ANR/RGC Joint Research Scheme sponsored by the Research Grants Council of the Hong Kong Special Administrative Region, China and France National Research Agency (Project No. A-CityU101/16), the Joint Funds of the National Natural Science Foundation of China under Key Program Grant U1713212, and CONACyT grant no. 221551.

PY - 2019/8

Y1 - 2019/8

N2 - This paper proposes an effective ensemble framework for tackling multi-objective optimization problems, by combining the advantages of various evolutionary operators and selection criteria that are run on multiple populations. A simple ensemble algorithm is realized as a prototype to demonstrate our proposed framework. Two mechanisms, namely competition and cooperation, are employed to drive the running of the ensembles. Competition is designed by adaptively running different evolutionary operators on multiple populations. The operator that better fits the problem’s characteristics will receive more computational resources, being rewarded by a decomposition-based credit assignment strategy. Cooperation is achieved by a cooperative selection of the offspring generated by different populations. In this way, the promising offspring from one population have chances to migrate into the other populations to enhance their convergence or diversity. Moreover, the population update information is further exploited to build an evolutionary potentiality model, which is used to guide the evolutionary process. Our experimental results show the superior performance of our proposed ensemble algorithms in solving most cases of a set of thirty-one test problems, which corroborates the advantages of our ensemble framework.

AB - This paper proposes an effective ensemble framework for tackling multi-objective optimization problems, by combining the advantages of various evolutionary operators and selection criteria that are run on multiple populations. A simple ensemble algorithm is realized as a prototype to demonstrate our proposed framework. Two mechanisms, namely competition and cooperation, are employed to drive the running of the ensembles. Competition is designed by adaptively running different evolutionary operators on multiple populations. The operator that better fits the problem’s characteristics will receive more computational resources, being rewarded by a decomposition-based credit assignment strategy. Cooperation is achieved by a cooperative selection of the offspring generated by different populations. In this way, the promising offspring from one population have chances to migrate into the other populations to enhance their convergence or diversity. Moreover, the population update information is further exploited to build an evolutionary potentiality model, which is used to guide the evolutionary process. Our experimental results show the superior performance of our proposed ensemble algorithms in solving most cases of a set of thirty-one test problems, which corroborates the advantages of our ensemble framework.

KW - competitive evolution

KW - cooperative selection.

KW - ensemble framework

KW - multi-objective optimization

KW - multiobjective optimization

KW - cooperative selection

KW - Competitive evolution

KW - ensemble framework (EF)

UR - http://www.scopus.com/inward/record.url?scp=85055895559&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/effective-ensemble-framework-multiobjective-optimization

U2 - 10.1109/TEVC.2018.2879078

DO - 10.1109/TEVC.2018.2879078

M3 - Article

VL - 23

SP - 645

EP - 659

JO - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1089-778X

IS - 4

M1 - 8519635

ER -