Offline Automatic Parameter Tuning of MOEA/D Using Genetic Algorithm

Pang，Lie Meng; Ishibuchi，Hisao; Shang，Ke

10.1109/SSCI44817.2019.9002787

2019-12-01

978-1-7281-2486-5

2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

1889-1897

6-9 Dec. 2019

Xiamen, China

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

The multiobjective evolutionary algorithm based on decomposition (MOEA/D) is one of the favorite algorithms in the evolutionary computation community. In this paper, a genetic algorithm is used to automatically tune the parameters for MOEA/D in an offline manner. We consider a version of MOEA/D with a normalization mechanism and two neighborhood structures (for mating and replacement). Our experimental results show that the automatically obtained implementation of MOEA/D outperforms MOEA/D with the default settings in their applications to the DTLZ and WFG test suites. The obtained implementation for each test problem also allows us to discover some potentially good parameter values that can lead to the performance improvement of MOEA/D on certain test problems.

automatic algorithm design hyper-heuristics MOEA/D multiobjective optimization offline parameter tuning

第一

英语

EI ; CPCI-S

[2017ZT07X386]

Computer Science

Computer Science, Artificial Intelligence

WOS:000555467201142

20201108277005

Artificial intelligence ; Genetic algorithms ; Multiobjective optimization

Artificial Intelligence:723.4 ; Optimization Techniques:921.5

2-s2.0-85080865773

Scopus

Southern University of Science and Technology,Shenzhen Key Laboratory of Computational Intelligence,University Key Laboratory of Evolving,Intelligent Systems of Guangdong Province,Shenzhen,China

Pang，Lie Meng,Ishibuchi，Hisao,Shang，Ke. Offline Automatic Parameter Tuning of MOEA/D Using Genetic Algorithm[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2019:1889-1897.