Balancing Exploration and Exploitation for Solving Large-scale Multiobjective Optimization via Attention Mechanism

TL;DR

This paper introduces LMOAM, a novel large-scale multiobjective optimization algorithm that employs an attention mechanism to assign weights to decision variables, effectively balancing exploration and exploitation in high-dimensional spaces.

Contribution

The paper proposes a new algorithm, LMOAM, which uses an attention mechanism to improve exploration and exploitation balance from the decision variable perspective in LSMOPs.

Findings

Experimental results validate the effectiveness of LMOAM across nine benchmark sets.

The attention mechanism enhances search efficiency in high-dimensional decision spaces.

LMOAM outperforms existing algorithms in balancing exploration and exploitation.

Abstract

Large-scale multiobjective optimization problems (LSMOPs) refer to optimization problems with multiple conflicting optimization objectives and hundreds or even thousands of decision variables. A key point in solving LSMOPs is how to balance exploration and exploitation so that the algorithm can search in a huge decision space efficiently. Large-scale multiobjective evolutionary algorithms consider the balance between exploration and exploitation from the individual's perspective. However, these algorithms ignore the significance of tackling this issue from the perspective of decision variables, which makes the algorithm lack the ability to search from different dimensions and limits the performance of the algorithm. In this paper, we propose a large-scale multiobjective optimization algorithm based on the attention mechanism, called (LMOAM). The attention mechanism will assign a unique weight to each decision variable, and LMOAM will use this weight to strike a balance between exploration and exploitation from the decision variable level. Nine different sets of LSMOP benchmarks are conducted to verify the algorithm proposed in this paper, and the experimental results validate the effectiveness of our design.