Unsupervised Learning of 3-Colorings Using Simplicial Higher-Order Neural Networks

Abstract

We propose Higher-Order Networks (HONs) for historically challenging problems for Graph Neural Networks (GNNs), such as Constraint Satisfaction Problems (CSPs). We apply a simple extension of GNNs to HONs and show its advantages for solving 3-coloring.

Cite

Text

Laird et al. "Unsupervised Learning of 3-Colorings Using Simplicial Higher-Order Neural Networks." ICML 2023 Workshops: TAGML, 2023.

Markdown

[Laird et al. "Unsupervised Learning of 3-Colorings Using Simplicial Higher-Order Neural Networks." ICML 2023 Workshops: TAGML, 2023.](https://mlanthology.org/icmlw/2023/laird2023icmlw-unsupervised/)

BibTeX

@inproceedings{laird2023icmlw-unsupervised,
  title     = {{Unsupervised Learning of 3-Colorings Using Simplicial Higher-Order Neural Networks}},
  author    = {Laird, Lucas and Walters, Robin and Gatterbauer, Wolfgang},
  booktitle = {ICML 2023 Workshops: TAGML},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/laird2023icmlw-unsupervised/}
}