No Cover Image

Journal article 371 views

Domain-informed graph neural networks: A quantum chemistry case study

Jay Morgan, Adeline Paiement, Christian Klinke Orcid Logo

Neural Networks, Volume: 165, Pages: 938 - 952

Swansea University Authors: Jay Morgan, Adeline Paiement, Christian Klinke Orcid Logo

Full text not available from this repository: check for access using links below.

Abstract

We explore different strategies to integrate prior domain knowledge into the design of graph neural networks (GNN). Our study is supported by a use-case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs. We integrate two elements of domain knowledg...

Full description

Published in: Neural Networks
ISSN: 0893-6080
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63771
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: We explore different strategies to integrate prior domain knowledge into the design of graph neural networks (GNN). Our study is supported by a use-case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs. We integrate two elements of domain knowledge into the design of the GNN to constrain and regularise its learning, towards higher accuracy and generalisation. First, knowledge on the existence of different types of relations/graph edges (e.g. chemical bonds in our case study) between nodes of the graph is used to modulate their interactions. We formulate and compare two strategies, namely specialised message production and specialised update of internal states. Second, knowledge of the relevance of some physical quantities is used to constrain the learnt features towards a higher physical relevance using a simple multi-task learning (MTL) paradigm. We explore the potential of MTL to better capture the underlying mechanisms behind the studied phenomenon. We demonstrate the general applicability of our two knowledge integrations by applying them to three architectures that rely on different mechanisms to propagate information between nodes and to update node states. Our implementations are made publicly available. To support these experiments, we release three new datasets of out-of-equilibrium molecules and crystals of various complexities.
Keywords: Graph neural network, Domain knowledge integration, Quantum chemistry application
College: Faculty of Science and Engineering
Start Page: 938
End Page: 952