English

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.

Keywords

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

R2 v1 2026-06-23T19:58:07.105Z