Manifold Interpolation for Large-Scale Multi-Objective Optimization via Generative Adversarial Networks

Abstract

Large-scale multiobjective optimization problems (LSMOPs) are characterized as involving hundreds or even thousands of decision variables and multiple conflicting objectives. An excellent algorithm for solving LSMOPs should find Pareto-optimal solutions with diversity and escape from local optima in the large-scale search space. Previous research has shown that these optimal solutions are uniformly distributed on the manifold structure in the low-dimensional space. However, traditional evolutionary algorithms for solving LSMOPs have some deficiencies in dealing with this structural manifold, resulting 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 this manifold, thereby improving the performance of evolutionary algorithms. We compare the proposed algorithm with several state-of-the-art algorithms on large-scale multiobjective benchmark functions. Experimental results have demonstrated the significant improvements achieved by this framework in solving LSMOPs.

References in corpus (7)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Semi-Supervised Learning with Deep Generative Models
• Improved Training of Wasserstein GANs
• Transfer Learning based Dynamic Multiobjective Optimization Algorithms
• MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
• Disconnected Manifold Learning for Generative Adversarial Networks
• Online Bagging for Anytime Transfer Learning