Domain-informed graph neural networks: a quantum chemistry case study - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2023

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

Abstract

We explore different strategies to integrate prior domain knowledge into the design of a deep neural network (DNN). We focus on graph neural networks (GNN), with 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 (chemical bonds) between atoms is used to modulate the interaction of nodes in the GNN. 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 paradigm. We demonstrate the general applicability of our knowledge integrations by applying them to two architectures that rely on different mechanisms to propagate information between nodes and to update node states
Fichier principal
Vignette du fichier
Chemistry_paper_preprint.pdf (1.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04142152 , version 1 (26-06-2023)

Identifiers

  • HAL Id : hal-04142152 , version 1

Cite

Jay Morgan, Adeline Paiement, Christian Klinke. Domain-informed graph neural networks: a quantum chemistry case study. 2023. ⟨hal-04142152⟩
32 View
23 Download

Share

Gmail Facebook X LinkedIn More