Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction
The prediction of material properties is a crucial challenge in the design of new materials. Traditional methods based on either trial-and-error experiments or large-scale density functional theory calculations are known to possess various limitations. Although recent machine learning (ML) methods h...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad9fcf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582698610196480 |
|---|---|
| author | Zexi Yang Qi Yu Yapeng Zhan Jiying Liu |
| author_facet | Zexi Yang Qi Yu Yapeng Zhan Jiying Liu |
| author_sort | Zexi Yang |
| collection | DOAJ |
| description | The prediction of material properties is a crucial challenge in the design of new materials. Traditional methods based on either trial-and-error experiments or large-scale density functional theory calculations are known to possess various limitations. Although recent machine learning (ML) methods have shed light on resolving this problem efficiently, the majority of ML models consider only the local atomic environment while ignoring the nonlocal correlations between atoms. Indeed, even the periodic patterns of the crystal structures are not seriously considered. Consequently, these issues lead to an insufficient understanding of the feature information of atoms and bonds. In this study, we propose a crystal graph convolutional neural network based on edge convolution (EdgeConv) and correlative self-attention, namely, EdgeConv-Graph attention neural network (GANN). This network is able to efficiently extract atomic and bonding feature information, while effectively learning the importance weights of all neighbouring nodes. Numerical experiments predicting the electronic structural properties of metal–organic frameworks show that the developed model achieves state-of-the-art performance. Moreover, the proposed model was applied to predict the heat capacity and thermal decomposition temperature of material, demonstrating the ability of this method to effectively generalise multiscale prediction tasks. |
| format | Article |
| id | doaj-art-9645f0bc37744fcda62058b7d4f262ad |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-9645f0bc37744fcda62058b7d4f262ad2025-01-29T11:24:53ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101502010.1088/2632-2153/ad9fcfIncorporating edge convolution and correlative self-attention into graph neural network for material properties predictionZexi Yang0https://orcid.org/0009-0006-6997-2125Qi Yu1https://orcid.org/0000-0002-5401-3494Yapeng Zhan2https://orcid.org/0009-0000-1857-1643Jiying Liu3https://orcid.org/0000-0003-0337-588XNational University of Defense Technology , Changsha 410000, People’s Republic of ChinaNational University of Defense Technology , Changsha 410000, People’s Republic of ChinaNational University of Defense Technology , Changsha 410000, People’s Republic of ChinaNational University of Defense Technology , Changsha 410000, People’s Republic of ChinaThe prediction of material properties is a crucial challenge in the design of new materials. Traditional methods based on either trial-and-error experiments or large-scale density functional theory calculations are known to possess various limitations. Although recent machine learning (ML) methods have shed light on resolving this problem efficiently, the majority of ML models consider only the local atomic environment while ignoring the nonlocal correlations between atoms. Indeed, even the periodic patterns of the crystal structures are not seriously considered. Consequently, these issues lead to an insufficient understanding of the feature information of atoms and bonds. In this study, we propose a crystal graph convolutional neural network based on edge convolution (EdgeConv) and correlative self-attention, namely, EdgeConv-Graph attention neural network (GANN). This network is able to efficiently extract atomic and bonding feature information, while effectively learning the importance weights of all neighbouring nodes. Numerical experiments predicting the electronic structural properties of metal–organic frameworks show that the developed model achieves state-of-the-art performance. Moreover, the proposed model was applied to predict the heat capacity and thermal decomposition temperature of material, demonstrating the ability of this method to effectively generalise multiscale prediction tasks.https://doi.org/10.1088/2632-2153/ad9fcfmaterial property predictionedge convolutioncorrelative self-attentiongraph convolutional neural networkmetal–organic frameworks |
| spellingShingle | Zexi Yang Qi Yu Yapeng Zhan Jiying Liu Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction Machine Learning: Science and Technology material property prediction edge convolution correlative self-attention graph convolutional neural network metal–organic frameworks |
| title | Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction |
| title_full | Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction |
| title_fullStr | Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction |
| title_full_unstemmed | Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction |
| title_short | Incorporating edge convolution and correlative self-attention into graph neural network for material properties prediction |
| title_sort | incorporating edge convolution and correlative self attention into graph neural network for material properties prediction |
| topic | material property prediction edge convolution correlative self-attention graph convolutional neural network metal–organic frameworks |
| url | https://doi.org/10.1088/2632-2153/ad9fcf |
| work_keys_str_mv | AT zexiyang incorporatingedgeconvolutionandcorrelativeselfattentionintographneuralnetworkformaterialpropertiesprediction AT qiyu incorporatingedgeconvolutionandcorrelativeselfattentionintographneuralnetworkformaterialpropertiesprediction AT yapengzhan incorporatingedgeconvolutionandcorrelativeselfattentionintographneuralnetworkformaterialpropertiesprediction AT jiyingliu incorporatingedgeconvolutionandcorrelativeselfattentionintographneuralnetworkformaterialpropertiesprediction |