Machine Learning-Enhanced Ant Colony Optimization for Column Generation

TL;DR

This paper introduces MLACO, a machine learning-enhanced ant colony optimization technique that accelerates column generation in optimization problems by predicting high-quality columns, significantly improving performance and reducing solution time.

Contribution

The paper presents a novel MLACO method that integrates machine learning with ant colony optimization to efficiently generate columns in column generation, enhancing optimization performance.

Findings

MLACO outperforms existing methods in bin packing with conflicts

Significant reduction in solution time when integrated into Branch-and-Price

Improved quality and speed of column generation in large-scale problems

Abstract

Column generation (CG) is a powerful technique for solving optimization problems that involve a large number of variables or columns. This technique begins by solving a smaller problem with a subset of columns and gradually generates additional columns as needed. However, the generation of columns often requires solving difficult subproblems repeatedly, which can be a bottleneck for CG. To address this challenge, we propose a novel method called machine learning enhanced ant colony optimization (MLACO), to efficiently generate multiple high-quality columns from a subproblem. Specifically, we train a ML model to predict the optimal solution of a subproblem, and then integrate this ML prediction into the probabilistic model of ACO to sample multiple high-quality columns. Our experimental results on the bin packing problem with conflicts show that the MLACO method significantly improves the performance of CG compared to several state-of-the-art methods. Furthermore, when our method is incorporated into a Branch-and-Price method, it leads to a significant reduction in solution time.