TY - JOUR
T1 - CIS Publication Spotlight [Publication Spotlight]
AU - Song, Yongduan
AU - Wu, Dongrui
AU - Coello, Carlos A.Coello
AU - Yannakakis, Georgios N.
AU - Tang, Huajin
AU - Cheung, Yiu Ming
N1 - Publisher copyright:
© 2024 IEEE
PY - 2024/2/1
Y1 - 2024/2/1
N2 - “Large-scale multiobjective optimization problems (LSMOPs) are characterized as optimization problems involving hundreds or even thousands of decision variables and multiple conflicting objectives. To solve LSMOPs, some algorithms designed a variety of strategies to track Pareto-optimal solutions (POSs) by assuming that the distribution of POSs follows a low-dimensional manifold. However, traditional genetic operators for solving LSMOPs have some deficiencies in dealing with the manifold, which often results in poor diversity, local optima, and inefficient searches. In this work, a generative adversarial network (GAN)-based manifold interpolation framework is proposed to learn the manifold and generate high-quality solutions on the manifold, thereby improving the optimization performance of evolutionary algorithms. We compare the proposed approach with several state-of-the-art algorithms on various large-scale multiobjective benchmark functions. The experimental results demonstrate that significant improvements have been achieved by the proposed framework in solving LSMOPs.”
AB - “Large-scale multiobjective optimization problems (LSMOPs) are characterized as optimization problems involving hundreds or even thousands of decision variables and multiple conflicting objectives. To solve LSMOPs, some algorithms designed a variety of strategies to track Pareto-optimal solutions (POSs) by assuming that the distribution of POSs follows a low-dimensional manifold. However, traditional genetic operators for solving LSMOPs have some deficiencies in dealing with the manifold, which often results in poor diversity, local optima, and inefficient searches. In this work, a generative adversarial network (GAN)-based manifold interpolation framework is proposed to learn the manifold and generate high-quality solutions on the manifold, thereby improving the optimization performance of evolutionary algorithms. We compare the proposed approach with several state-of-the-art algorithms on various large-scale multiobjective benchmark functions. The experimental results demonstrate that significant improvements have been achieved by the proposed framework in solving LSMOPs.”
UR - http://www.scopus.com/inward/record.url?scp=85183187553&partnerID=8YFLogxK
U2 - 10.1109/MCI.2023.3333472
DO - 10.1109/MCI.2023.3333472
M3 - Journal article
AN - SCOPUS:85183187553
SN - 1556-603X
VL - 19
SP - 24
EP - 26
JO - IEEE Computational Intelligence Magazine
JF - IEEE Computational Intelligence Magazine
IS - 1
ER -