A multi-feature fusion-based evolutionary algorithm for large-scale sparse multi-objective optimization problems

Abstract

Large-scale sparse multi-objective optimization problems are common and present significant challenges in scientific research and engineering practice. The primary characteristics of these problems include the high dimensionality of decision variables and the sparsity of the solution set, which greatly increase the problem’s difficulty. During the algorithmic solution process, the interference of non-critical variables reduces the algorithm’s solving efficiency and negatively impacts the quality of the solution set. Therefore, this paper proposes a large-scale sparse multi-objective evolutionary algorithm based on multi-feature fusion, comprehensively considering the importance of decision variables from multiple aspects. First, we introduce a reference point perturbation clustering method. By evenly distributing reference points in the decision space, we control the perturbation of decision variables. The perturbed decision variables are clustered, and an activation function is used to transform the clustering results into contribution values that assess the importance of the decision variables. Second, we propose a sparse feature detection method to mine sparse features from the sparse information of the decision variables, evaluating the informational content of the decision variables. This information is used to filter decision variables to reduce the search space. Finally, the filtered decision variables are competitively optimized using contribution values. Experiments on eight benchmark problems and three real-world applications demonstrate that the algorithm surpasses current state-of-the-art large-scale sparse multi-objective evolutionary algorithms in terms of convergence speed and solution set quality.