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} .
@article{arxiv.2202.04910,
title = {Instance-wise algorithm configuration with graph neural networks},
author = {Romeo Valentin and Claudio Ferrari and Jérémy Scheurer and Andisheh Amrollahi and Chris Wendler and Max B. Paulus},
journal= {arXiv preprint arXiv:2202.04910},
year = {2022}
}