TY - JOUR
T1 - Learning-assisted Search Path Reconstruction Empowers Evolution Algorithm for Optimization
AU - Song, Yaotong
AU - Wang, Kaiyu
AU - Zhan, Zhi Hui
AU - Lei, Zhenyu
AU - Gao, Shangce
N1 - Publisher Copyright:
© 2025 IEEE. All rights reserved.
PY - 2025
Y1 - 2025
N2 - Evolutionary algorithms serve as a pivotal tool in addressing black-box problems, finding widespread applications across diverse academic disciplines and engineering domains. Despite their utility, these algorithms often confront challenges when navigating complex search spaces, impeding a comprehensive exploration of potential solutions. Solely depending on the algorithm’s exploration abilities falls short of fully harnessing the rich information contained within search spaces. To unlock the full potential of solution spaces, we introduce a deep learning method for the reconstruction of the search path. Specifically, discrete data sampled by evolutionary operators during the exploration process are collected, and a uniquely designed fully connected neural network is employed to reconstruct the exploration paths. The neural network’s robust fitting capability facilitates the transformation of initially discrete sampled information into a continuous form. By capitalizing on the reconstructed solution space information, the algorithm excels in identifying superior solutions. We refer to this method of deep learning-based search path reconstruction evolution strategy algorithm (DLES). The effectiveness of DLES is validated across multiple datasets, including CEC 2014, CEC 2018, CEC 2022 and BBOB. Experimental results, compared to several state-of-the-art algorithms, affirm the superiority of the DLES algorithm.
AB - Evolutionary algorithms serve as a pivotal tool in addressing black-box problems, finding widespread applications across diverse academic disciplines and engineering domains. Despite their utility, these algorithms often confront challenges when navigating complex search spaces, impeding a comprehensive exploration of potential solutions. Solely depending on the algorithm’s exploration abilities falls short of fully harnessing the rich information contained within search spaces. To unlock the full potential of solution spaces, we introduce a deep learning method for the reconstruction of the search path. Specifically, discrete data sampled by evolutionary operators during the exploration process are collected, and a uniquely designed fully connected neural network is employed to reconstruct the exploration paths. The neural network’s robust fitting capability facilitates the transformation of initially discrete sampled information into a continuous form. By capitalizing on the reconstructed solution space information, the algorithm excels in identifying superior solutions. We refer to this method of deep learning-based search path reconstruction evolution strategy algorithm (DLES). The effectiveness of DLES is validated across multiple datasets, including CEC 2014, CEC 2018, CEC 2022 and BBOB. Experimental results, compared to several state-of-the-art algorithms, affirm the superiority of the DLES algorithm.
KW - Evolutionary computation
KW - artificial neural network
KW - deep learning
KW - search space reconstruction
KW - single-objective optimization
UR - http://www.scopus.com/inward/record.url?scp=105000187388&partnerID=8YFLogxK
U2 - 10.1109/TEVC.2025.3550259
DO - 10.1109/TEVC.2025.3550259
M3 - 学術論文
AN - SCOPUS:105000187388
SN - 1089-778X
JO - IEEE Transactions on Evolutionary Computation
JF - IEEE Transactions on Evolutionary Computation
ER -