Finding Hamiltonian Cycles with Graph Neural Networks

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 computat...

Full description

Bibliographic Details

Published in:	2023 International Symposium on Image and Signal Processing and Analysis (ISPA) pp. 1 - 6
Main Authors:	Bosnic, Filip, Sikic, Mile
Format:	Conference Proceeding
Language:	English
Published:	IEEE 18.09.2023
Subjects:	Graph algorithms Graphics processing units Heuristics design Machine learning Machine learning algorithms Neural nets NP-hard problem Signal processing Signal processing algorithms Supervised learning Training
ISSN:	1849-2266
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!