期刊
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
卷 27, 期 4, 页码 1042-1056出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TEVC.2022.3189029
关键词
Differential evolution (DE); evolutionary multitasking (EMT); generative adversarial networks (GANs); multiobjective optimization
Evolutionary multitasking (EMT) is a promising topic in evolutionary computation where multiple related optimization tasks can be solved simultaneously through knowledge sharing. This article proposes EMT-GS, an EMT algorithm for multiobjective optimization, based on generative strategies using generative adversarial networks (GANs) and inertial differential evolution (IDE). The performance of EMT-GS is evaluated on three multitasking multiobjective benchmark problems, showing its competitiveness compared to other state-of-the-art multiobjective EMT algorithms.
Evolutionary multitasking (EMT) is one of the emerging topics in evolutionary computation. EMT can solve multiple related optimization tasks simultaneously and enhance the optimization of each task via knowledge sharing among tasks. Many EMT algorithms have been proposed and achieved success in various problems, yet EMT for multiobjective optimization remains a big challenge. The existing multiobjective EMT algorithms tend to suffer from slow convergence and difficulty in generating high-quality knowledge. To alleviate these issues, this article proposes a new EMT algorithm, namely, EMT-GS for multiobjective optimization based on two generative strategies. Particularly, generative adversarial networks (GANs) and inertial differential evolution (IDE) are introduced to generate transferable knowledge and offspring, respectively. A GAN is trained periodically for each source-target task pair, based on which helpful knowledge is generated from the source task and transferred to boost the solving of the target task. To accelerate the population convergence, the IDE strategy is put forward to generate offspring in a promising direction according to the individuals from the previous generation and the transferred knowledge. The performance of EMT-GS is validated on three multitasking multiobjective benchmark problems. The experimental results highlight the excellent competitiveness of EMT-GS compared to other state-of-the-art multiobjective EMT algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据