Neural Algorithmic Reasoning for Combinatorial Optimisation

Dobrik Georgiev Georgiev, Danilo Numeroso, Davide Bacciu, Pietro Lio

Keywords: Neural Algorithmic Reasoning, Neural Combinatorial Optimisation, Graph Neural Networks

Abstract: Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms. The long-term objective is to outperform hand-designed heuristics for NP-hard/complete problems by learning to generate superior solutions solely from training data. Current neural-based methods for solving CO problems often overlook the inherent "algorithmic" nature of the problems. In contrast, heuristics designed for CO problems, e.g. TSP, frequently leverage well-established algorithms, such as those for finding the minimum spanning tree. In this paper, we propose leveraging recent advancements in neural algorithmic reasoning to improve the learning of CO problems. Specifically, we suggest pre-training our neural model on relevant algorithms before training it on CO instances. Our results demonstrate that, using this learning setup, we achieve superior performance compared to non-algorithmically informed deep learning models.

Submission Type: Full paper proceedings track submission (max 9 main pages).

Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.

Software: https://github.com/danilonumeroso/conar

Submission Number: 83