A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimization

TL;DR

This paper introduces LH-CC, a learning-based framework that adaptively selects optimizers for heterogeneous large-scale global optimization, significantly improving solution quality and efficiency.

Contribution

It proposes a novel meta-agent approach to dynamically choose optimizers for diverse subproblems in H-LSGO, addressing limitations of fixed-optimizer methods.

Findings

LH-CC outperforms state-of-the-art baselines on complex 3000-dimensional problems.

The framework demonstrates robust generalization across different problem instances and horizons.

Dynamic optimizer selection is crucial for effectively solving heterogeneous large-scale optimization problems.

Abstract

Cooperative Coevolution (CC) effectively addresses Large-Scale Global Optimization (LSGO) via decomposition but struggles with the emerging class of Heterogeneous LSGO (H-LSGO) problems arising from real-world applications, where subproblems exhibit diverse dimensions and distinct landscapes. The prevailing CC paradigm, relying on a fixed low-dimensional optimizer, often fails to navigate this heterogeneity. To address this limitation, we propose the Learning-Based Heterogeneous Cooperative Coevolution Framework (LH-CC). By formulating the optimization process as a Markov Decision Process, LH-CC employs a meta-agent to adaptively select the most suitable optimizer for each subproblem. We also introduce a flexible benchmark suite to generate diverse H-LSGO problem instances. Extensive experiments on 3000-dimensional problems with complex coupling relationships demonstrate that LH-CC achieves superior solution quality and computational efficiency compared to state-of-the-art baselines. Furthermore, the framework exhibits robust generalization across varying problem instances, optimization horizons, and optimizers. Our findings reveal that dynamic optimizer selection is a pivotal strategy for solving complex H-LSGO problems.