Year: 2023
Type: conference-paper
Abstract: We train a small message-passing graph neural network to predict Hamiltonian cycles on Erdos-Renyl random graphs in a critical regime. It outperforms existing hand-crafted heuristics after about 2.5 hours of training on a single GPU. Our findings encourage an alternative approach to solving computationally demanding (NP-hard) problems arising in practice. Instead of devising a heuristic by hand, one can train it end-to-end using a neural network. This has several advantages. Firstly, it is relatively quick and requires little problem-specific knowledge. Secondly, the network can adjust to the distribution of training samples, improving the performance on the most relevant problem instances. The model is trained using supervised learning on artificially created problem instances; this training procedure does not use an existing solver to produce the super-vised signal. Finally, the model generalizes well to larger graph sizes and retains reasonable performance even on graphs eight times the original size.
Authors: Filip Bosnić, Mile Šikić
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4387785448