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

Hongwei Du, Jiamin Wang, Jian Hui, Lanting Zhang, Hong Wang
1/5/2025
cond-mat.mtrl-scics.LG

No official code found. Best implementation: dhw059/DenseGNN (30 stars, last commit 2025-01-03).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

dhw059/DenseGNNCommunity100%

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

309Python, Jupyter NotebookJan 30, 20241 years ago

Similar Papers

CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials

88% match1 repo312023

Enhancing material property prediction with ensemble deep graph convolutional networks

86% match2024

DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials

85% match2023

CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction

85% match1 repo12024

MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network

85% match2023

Do Graph Neural Networks Work for High Entropy Alloys?

85% match1 repo92024

Cite this paper

@article{du2025densegnn,
  title  = {DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules},
  author = {Hongwei Du and Jiamin Wang and Jian Hui and Lanting Zhang and Hong Wang},
  year   = {2025},
  eprint = {2501.03278},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.03278v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.03278.svg)](https://codeofpaper.com/paper/2501.03278)

Discussion