Adaptively Allocating Search Effort in Challenging Many-Objective Optimization Problems

Hai Lin Liu, Lei Chen, Qingfu Zhang, Kalyanmoy Deb

Research output: Contribution to journalArticle

Abstract

An effective allocation of search effort is important in multi-objective optimization, particularly in many-objective optimization problems. This paper presents a new adaptive search effort allocation strategy for MOEA/D-M2M, a recent MOEA/D algorithm for challenging Many-Objective Optimization Problems (MaOPs). This proposed method adaptively adjusts the subregions of its subproblems by detecting the importance of different objectives in an adaptive manner. More specifically, it periodically resets the subregion setting based on the distribution of the current solutions in the objective space such that the search effort is not wasted on unpromising regions. The basic idea is that the current population can be regarded as an approximation to the Pareto front (PF) and thus one can implicitly estimate the shape of the PF and such estimation can be used for adjusting the search focus. The performance of proposed algorithm has been verified by comparing it with eight representative and competitive algorithms on a set of degenerated many-objective optimization problems with disconnected and connected PFs. Performances of the proposed algorithm on a number of non-degenerated test instances with connected and disconnected PFs are also studied.

Original languageEnglish (US)
JournalIEEE Transactions on Evolutionary Computation
DOIs
StateAccepted/In press - Jul 12 2017

Profile

Optimization problem
Pareto front
Multiobjective optimization
Multi-objective optimization
Approximation
Estimate

Keywords

  • adaptive allocation.
  • evolutionary algorithm
  • Many-objective optimization
  • MOEA/D

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Computational Theory and Mathematics

Cite this

Adaptively Allocating Search Effort in Challenging Many-Objective Optimization Problems. / Liu, Hai Lin; Chen, Lei; Zhang, Qingfu; Deb, Kalyanmoy.

In: IEEE Transactions on Evolutionary Computation, 12.07.2017.

Research output: Contribution to journalArticle

Liu, Hai Lin; Chen, Lei; Zhang, Qingfu; Deb, Kalyanmoy / Adaptively Allocating Search Effort in Challenging Many-Objective Optimization Problems.

In: IEEE Transactions on Evolutionary Computation, 12.07.2017.

Research output: Contribution to journalArticle

@article{a714c9d901f44878a6d08c9b29e4116a,
title = "Adaptively Allocating Search Effort in Challenging Many-Objective Optimization Problems",
abstract = "An effective allocation of search effort is important in multi-objective optimization, particularly in many-objective optimization problems. This paper presents a new adaptive search effort allocation strategy for MOEA/D-M2M, a recent MOEA/D algorithm for challenging Many-Objective Optimization Problems (MaOPs). This proposed method adaptively adjusts the subregions of its subproblems by detecting the importance of different objectives in an adaptive manner. More specifically, it periodically resets the subregion setting based on the distribution of the current solutions in the objective space such that the search effort is not wasted on unpromising regions. The basic idea is that the current population can be regarded as an approximation to the Pareto front (PF) and thus one can implicitly estimate the shape of the PF and such estimation can be used for adjusting the search focus. The performance of proposed algorithm has been verified by comparing it with eight representative and competitive algorithms on a set of degenerated many-objective optimization problems with disconnected and connected PFs. Performances of the proposed algorithm on a number of non-degenerated test instances with connected and disconnected PFs are also studied.",
keywords = "adaptive allocation., evolutionary algorithm, Many-objective optimization, MOEA/D",
author = "Liu, {Hai Lin} and Lei Chen and Qingfu Zhang and Kalyanmoy Deb",
year = "2017",
month = "7",
doi = "10.1109/TEVC.2017.2725902",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1089-778X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Adaptively Allocating Search Effort in Challenging Many-Objective Optimization Problems

AU - Liu,Hai Lin

AU - Chen,Lei

AU - Zhang,Qingfu

AU - Deb,Kalyanmoy

PY - 2017/7/12

Y1 - 2017/7/12

N2 - An effective allocation of search effort is important in multi-objective optimization, particularly in many-objective optimization problems. This paper presents a new adaptive search effort allocation strategy for MOEA/D-M2M, a recent MOEA/D algorithm for challenging Many-Objective Optimization Problems (MaOPs). This proposed method adaptively adjusts the subregions of its subproblems by detecting the importance of different objectives in an adaptive manner. More specifically, it periodically resets the subregion setting based on the distribution of the current solutions in the objective space such that the search effort is not wasted on unpromising regions. The basic idea is that the current population can be regarded as an approximation to the Pareto front (PF) and thus one can implicitly estimate the shape of the PF and such estimation can be used for adjusting the search focus. The performance of proposed algorithm has been verified by comparing it with eight representative and competitive algorithms on a set of degenerated many-objective optimization problems with disconnected and connected PFs. Performances of the proposed algorithm on a number of non-degenerated test instances with connected and disconnected PFs are also studied.

AB - An effective allocation of search effort is important in multi-objective optimization, particularly in many-objective optimization problems. This paper presents a new adaptive search effort allocation strategy for MOEA/D-M2M, a recent MOEA/D algorithm for challenging Many-Objective Optimization Problems (MaOPs). This proposed method adaptively adjusts the subregions of its subproblems by detecting the importance of different objectives in an adaptive manner. More specifically, it periodically resets the subregion setting based on the distribution of the current solutions in the objective space such that the search effort is not wasted on unpromising regions. The basic idea is that the current population can be regarded as an approximation to the Pareto front (PF) and thus one can implicitly estimate the shape of the PF and such estimation can be used for adjusting the search focus. The performance of proposed algorithm has been verified by comparing it with eight representative and competitive algorithms on a set of degenerated many-objective optimization problems with disconnected and connected PFs. Performances of the proposed algorithm on a number of non-degenerated test instances with connected and disconnected PFs are also studied.

KW - adaptive allocation.

KW - evolutionary algorithm

KW - Many-objective optimization

KW - MOEA/D

UR - http://www.scopus.com/inward/record.url?scp=85023597896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023597896&partnerID=8YFLogxK

U2 - 10.1109/TEVC.2017.2725902

DO - 10.1109/TEVC.2017.2725902

M3 - Article

JO - IEEE Transactions on Evolutionary Computation

T2 - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1089-778X

ER -