Last-X-Generation Archiving Strategy for Multi-Objective Evolutionary Algorithms

Tianye Shu1; Yang Nan1; Ke Shang2,3; Hisao Ishibuchi1

10.1109/CEC60901.2024.10612171

2024-07-05

979-8-3503-0837-2

2024 IEEE Congress on Evolutionary Computation (CEC)

30 June-5 July 2024

Yokohama, Japan

For evolutionary multi-objective optimization algorithms (EMOAs), an external archive can be utilized for saving good solutions found throughout the evolutionary process. Recent studies showed that a solution set selected from an external archive is usually superior to the final population. That is, the incorporation of an external archive improves the performance of EMOAs. However, the computation time for maintaining an external archive is long, especially when the archive size is large. To solve this issue, a simple archiving strategy is to save all solutions generated in the last several generations. In this paper, we examine this archiving strategy for three representative EMOAs on artificial test problems (Minus-DTLZ and WFG) and real-world problems (RE). Our results show that archiving the last several generations clearly improves the performance of EMOAs without severely increasing the computation time.

第一

EI

1.Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China
2.Southern University of Science and Technology, Shenzhen, China
3.National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China

Tianye Shu,Yang Nan,Ke Shang,et al. Last-X-Generation Archiving Strategy for Multi-Objective Evolutionary Algorithms[C],2024.