Saved in:
Bibliographic Details
Main Authors: Jin, Luozhijie, Du, Zijian, Shu, Le, Mei, Yongfeng, Zhang, Hao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.09755
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911760224616448
author Jin, Luozhijie
Du, Zijian
Shu, Le
Mei, Yongfeng
Zhang, Hao
author_facet Jin, Luozhijie
Du, Zijian
Shu, Le
Mei, Yongfeng
Zhang, Hao
contents In this work, we propose a novel approach to generate universal atomic embeddings, significantly enhancing the representational and accuracy aspects of atomic embeddings, which ultimately improves the accuracy of property prediction. Moreover, we demonstrate the excellent transferability of universal atomic embeddings across different databases and various property tasks. Our approach centers on developing the CrystalTransformer model. Unlike traditional methods, this model does not possess a fundamental graph network architecture but utilizes the Transformer architecture to extract latent atomic features. This allows the CrystalTransformer to mitigate the inherent topological information bias of graph neural networks while maximally preserving the atomic chemical information, making it more accurate in encoding complex atomic features and thereby offering a deeper understanding of the atoms in materials. In our research, we highlight the advantages of CrystalTransformer in generating universal atomic embeddings through comparisons with current mainstream graph neural network models. Furthermore, we validate the effectiveness of universal atomic embeddings in enhancing the accuracy of model predictions for properties and demonstrate their transferability across different databases and property tasks through various experiments. As another key aspect of our study, we discover the strong physical interpretability implied in universal atomic embeddings through clustering and correlation analysis, indicating the immense potential of our universal atomic embeddings as atomic fingerprints.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09755
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Crystal Transformer Based Universal Atomic Embedding for Accurate and Transferable Prediction of Materials Properties
Jin, Luozhijie
Du, Zijian
Shu, Le
Mei, Yongfeng
Zhang, Hao
Materials Science
Computational Physics
In this work, we propose a novel approach to generate universal atomic embeddings, significantly enhancing the representational and accuracy aspects of atomic embeddings, which ultimately improves the accuracy of property prediction. Moreover, we demonstrate the excellent transferability of universal atomic embeddings across different databases and various property tasks. Our approach centers on developing the CrystalTransformer model. Unlike traditional methods, this model does not possess a fundamental graph network architecture but utilizes the Transformer architecture to extract latent atomic features. This allows the CrystalTransformer to mitigate the inherent topological information bias of graph neural networks while maximally preserving the atomic chemical information, making it more accurate in encoding complex atomic features and thereby offering a deeper understanding of the atoms in materials. In our research, we highlight the advantages of CrystalTransformer in generating universal atomic embeddings through comparisons with current mainstream graph neural network models. Furthermore, we validate the effectiveness of universal atomic embeddings in enhancing the accuracy of model predictions for properties and demonstrate their transferability across different databases and property tasks through various experiments. As another key aspect of our study, we discover the strong physical interpretability implied in universal atomic embeddings through clustering and correlation analysis, indicating the immense potential of our universal atomic embeddings as atomic fingerprints.
title Crystal Transformer Based Universal Atomic Embedding for Accurate and Transferable Prediction of Materials Properties
topic Materials Science
Computational Physics
url https://arxiv.org/abs/2401.09755