Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks

TL;DR

This paper introduces a multi-objective evolutionary algorithm that leverages GANs to generate offspring solutions, effectively handling high-dimensional problems with limited training data, and demonstrating superior performance on benchmark tests.

Contribution

It presents a novel GAN-driven evolutionary algorithm that overcomes data scarcity and high-dimensionality challenges in multi-objective optimization.

Findings

Effective in high-dimensional decision spaces

Generates promising offspring with limited training data

Outperforms existing methods on benchmark problems

Abstract

Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models.Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality.To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial networks (GANs).At each generation of the proposed algorithm, the parent solutions are first classified into \emph{real} and \emph{fake} samples to train the GANs; then the offspring solutions are sampled by the trained GANs.Thanks to the powerful generative ability of the GANs, our proposed algorithm is capable of generating promising offspring solutions in high-dimensional decision space with limited training data.The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables.Experimental results on these test problems demonstrate the effectiveness of the proposed algorithm.