arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.01829cond-mat.mtrl-sci
收藏

改进材料性能预测的原子线图神经网络

Atomistic Line Graph Neural Network for Improved Materials Property Predictions

Kamal Choudhary, Brian DeCost

摘要:

图神经网络(GNN)已被证明为原子材料表示和建模提供了实质性的性能改进,与基于机器学习模型相比。虽然大多数现有的GNN模型的原子预测是基于原子距离信息,他们没有明确纳入键角,这是关键的区分许多原子结构。此外,已知许多材料性质对键角的微小变化敏感。我们提出了一个原子线图神经网络(ALIGNN),GNN架构,执行消息传递的原子间键合图和它的线图对应的键角。我们证明,角度信息可以明确和有效地包括在内,从而提高性能的多个原子预测任务。我们ALIGNN模型预测52固态和分子性质可在JARVIS-DFT,材料项目,和QM 9数据库。ALIGNN在原子预测任务上的准确率高达85%,并且模型训练速度更好或相当。

英文摘要:

Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks by up to 85% in accuracy with better or comparable model training speed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑