Learning with Molecules beyond Graph Neural Networks
Machine Learning
2020-11-09 v1 Artificial Intelligence
Logic in Computer Science
Neural and Evolutionary Computing
Abstract
We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.
Cite
@article{arxiv.2011.03488,
title = {Learning with Molecules beyond Graph Neural Networks},
author = {Gustav Sourek and Filip Zelezny and Ondrej Kuzelka},
journal= {arXiv preprint arXiv:2011.03488},
year = {2020}
}
Comments
accepted to Machine Learning for Molecules Workshop @ NeurIPS 2020