Manifold Interpolation for Large-Scale Multi-Objective Optimization via Generative Adversarial Networks
This work aims to improve the diversity and efficiency of finding Pareto-optimal solutions for researchers and practitioners dealing with large-scale multi-objective optimization problems, which is an incremental improvement.
This paper addresses large-scale multi-objective optimization problems (LSMOPs) by proposing a GAN-based manifold interpolation framework. This framework learns the underlying manifold structure of Pareto-optimal solutions and generates high-quality solutions on it, leading to significant performance improvements over state-of-the-art algorithms on benchmark functions.
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.