Instance-wise algorithm configuration with graph neural networks

TL;DR

This paper introduces a graph neural network approach to predict solver configurations for MILP problems, significantly improving solver efficiency and performance in a competitive setting.

Contribution

The paper presents a novel supervised learning method using graph neural networks to predict solver configurations for MILP instances, outperforming default settings.

Findings

Improved solver performance by up to 35% on benchmark problems.

Achieved 3rd place in the ML4CO competition leaderboard.

Code is publicly available for reproducibility.

Abstract

We present our submission for the configuration task of the Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition. The configuration task is to predict a good configuration of the open-source solver SCIP to solve a mixed integer linear program (MILP) efficiently. We pose this task as a supervised learning problem: First, we compile a large dataset of the solver performance for various configurations and all provided MILP instances. Second, we use this data to train a graph neural network that learns to predict a good configuration for a specific instance. The submission was tested on the three problem benchmarks of the competition and improved solver performance over the default by 12% and 35% and 8% across the hidden test instances. We ranked 3rd out of 15 on the global leaderboard and won the student leaderboard. We make our code publicly available at \url{https://github.com/RomeoV/ml4co-competition} .