Performance Comparison of EMO Algorithms on Test Problems with Different Search Space Shape

Tanigaki, Yuki1; Nojima, Yusuke1; Ishibuchi, Hisao1,2

10.1109/IFSA-SCIS.2017.8023314

2017

2377-6870

978-1-5090-4918-9

2017 JOINT 17TH WORLD CONGRESS OF INTERNATIONAL FUZZY SYSTEMS ASSOCIATION AND 9TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS (IFSA-SCIS)

1-6

27-30 June 2017

1-1-20, Nionohama, Otsu, Japan

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

IEEE

We examine the performance of evolutionary multi-objective optimization (EMO) algorithms on various shapes of the search space in the objective space (i.e., the feasible region in the objective space). To analyze the advantage and disadvantage of each EMO algorithm on the shape of the search space, we propose a meta-optimization method which can automatically create multi-objective optimization problems (MOPs) for clarifying the advantage and disadvantage of EMO algorithms. In particular, we propose a two-level model to generate such MOPs. In the upper level, MOPs are handled as solutions. Some design variables of each MOP are optimized in this level. In the lower level, each MOP is used to calculate the relative performance between two EMO algorithms. The relative performance is regarded as the fitness of the MOP in the upper level. Thus, by maximizing the relative performance, we can obtain an MOP which differentiates the search performance between two EMO algorithms. Through computational experiments, we obtained two interesting observations. One is that Pareto dominance-based EMO algorithms have a low escaping ability from local Pareto-optimal regions. The other is that it is difficult for decomposition-and indicator-based EMO algorithms to find solutions along the entire Pareto front.

Evolutionary multi-objective optimization (EMO) meta-optimization problem generation.

其他

英语

CPCI-S ; EI

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:000427063700096

20174104266037

Fuzzy systems ; Intelligent computing ; Intelligent systems ; Multiobjective optimization ; Pareto principle ; Pinch effect ; Soft computing

Computer Software, Data Handling and Applications:723 ; Artificial Intelligence:723.4 ; Optimization Techniques:921.5 ; Systems Science:961

Web of Science

1.Osaka Prefecture Univ, Grad Sch Engn, Dept Comp Sci & Intelligent Syst, Sakai, Osaka 5998531, Japan
2.Southern Univ Sci & Technol SUSTech, Dept Comp Sci & Engn, Shenzhen, Guangdong, Peoples R China

Tanigaki, Yuki,Nojima, Yusuke,Ishibuchi, Hisao. Performance Comparison of EMO Algorithms on Test Problems with Different Search Space Shape[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:1-6.