DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Du, Hongwei, Wang, Jiamin, Hui, Jian, Zhang, Lanting, Wang, Hong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910774013722624
author Du, Hongwei
Wang, Jiamin
Hui, Jian
Zhang, Lanting
Wang, Hong
author_facet Du, Hongwei
Wang, Jiamin
Hui, Jian
Zhang, Lanting
Wang, Hong
contents Generative models generate vast numbers of hypothetical materials, necessitating fast, accurate models for property prediction. Graph Neural Networks (GNNs) excel in this domain but face challenges like high training costs, domain adaptation issues, and over-smoothing. We introduce DenseGNN, which employs Dense Connectivity Network (DCN), Hierarchical Node-Edge-Graph Residual Networks (HRN), and Local Structure Order Parameters Embedding (LOPE) to address these challenges. DenseGNN achieves state-of-the-art performance on datasets such as JARVIS-DFT, Materials Project, and QM9, improving the performance of models like GIN, Schnet, and Hamnet on materials datasets. By optimizing atomic embeddings and reducing computational costs, DenseGNN enables deeper architectures and surpasses other GNNs in crystal structure distinction, approaching X-ray diffraction method accuracy. This advances materials discovery and design.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
Du, Hongwei
Wang, Jiamin
Hui, Jian
Zhang, Lanting
Wang, Hong
Materials Science
Machine Learning
Generative models generate vast numbers of hypothetical materials, necessitating fast, accurate models for property prediction. Graph Neural Networks (GNNs) excel in this domain but face challenges like high training costs, domain adaptation issues, and over-smoothing. We introduce DenseGNN, which employs Dense Connectivity Network (DCN), Hierarchical Node-Edge-Graph Residual Networks (HRN), and Local Structure Order Parameters Embedding (LOPE) to address these challenges. DenseGNN achieves state-of-the-art performance on datasets such as JARVIS-DFT, Materials Project, and QM9, improving the performance of models like GIN, Schnet, and Hamnet on materials datasets. By optimizing atomic embeddings and reducing computational costs, DenseGNN enables deeper architectures and surpasses other GNNs in crystal structure distinction, approaching X-ray diffraction method accuracy. This advances materials discovery and design.
title DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2501.03278