Solving Large-Scale Multi-Objective Optimization via Probabilistic Prediction Model

TL;DR

This paper introduces LT-PPM, a probabilistic prediction model that improves search efficiency and reduces computational costs in large-scale multi-objective optimization by maintaining population diversity and avoiding exponential complexity growth.

Contribution

The paper proposes a novel LT-PPM algorithm that enhances diversity and efficiency in LSMOP using a trend prediction model and importance sampling, with complexity independent of decision variable count.

Findings

Significant performance improvements over state-of-the-art algorithms.

Reduced computational complexity independent of decision variable number.

Effective maintenance of population diversity in large-scale problems.

Abstract

The main feature of large-scale multi-objective optimization problems (LSMOP) is to optimize multiple conflicting objectives while considering thousands of decision variables at the same time. An efficient LSMOP algorithm should have the ability to escape the local optimal solution from the huge search space and find the global optimal. Most of the current researches focus on how to deal with decision variables. However, due to the large number of decision variables, it is easy to lead to high computational cost. Maintaining the diversity of the population is one of the effective ways to improve search efficiency. In this paper, we propose a probabilistic prediction model based on trend prediction model and generating-filtering strategy, called LT-PPM, to tackle the LSMOP. The proposed method enhances the diversity of the population through importance sampling. At the same time, due to the adoption of an individual-based evolution mechanism, the computational cost of the proposed method is independent of the number of decision variables, thus avoiding the problem of exponential growth of the search space. We compared the proposed algorithm with several state-of-the-art algorithms for different benchmark functions. The experimental results and complexity analysis have demonstrated that the proposed algorithm has significant improvement in terms of its performance and computational efficiency in large-scale multi-objective optimization.