Crystal Hypergraph Convolutional Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Heilman, Alexander J., Gong, Weiyi, Yan, Qimin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915026068045824
author Heilman, Alexander J.
Gong, Weiyi
Yan, Qimin
author_facet Heilman, Alexander J.
Gong, Weiyi
Yan, Qimin
contents Graph representations of solid state materials that encode only interatomic distance lack geometrical resolution, resulting in degenerate representations that may map distinct structures to equivalent graphs. Here we propose a hypergraph representation scheme for materials that allows for the association of higher-order geometrical information with hyperedges. Hyperedges generalize edges to connected sets of more than two nodes, and may be used to represent triplets and local environments of atoms in materials. This generalization of edges requires a different approach in graph convolution, three of which are developed in this paper. Results presented here focus on the improved performance of models based on both pair-wise edges and local environment hyperedges. These results demonstrate that hypergraphs are an effective method for incorporating geometrical information in material representations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12616
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Crystal Hypergraph Convolutional Networks
Heilman, Alexander J.
Gong, Weiyi
Yan, Qimin
Materials Science
Graph representations of solid state materials that encode only interatomic distance lack geometrical resolution, resulting in degenerate representations that may map distinct structures to equivalent graphs. Here we propose a hypergraph representation scheme for materials that allows for the association of higher-order geometrical information with hyperedges. Hyperedges generalize edges to connected sets of more than two nodes, and may be used to represent triplets and local environments of atoms in materials. This generalization of edges requires a different approach in graph convolution, three of which are developed in this paper. Results presented here focus on the improved performance of models based on both pair-wise edges and local environment hyperedges. These results demonstrate that hypergraphs are an effective method for incorporating geometrical information in material representations.
title Crystal Hypergraph Convolutional Networks
topic Materials Science
url https://arxiv.org/abs/2411.12616