arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.09932cond-mat.mtrl-sciphysics.comp-ph
收藏

基于晶体图卷积神经网络的材料信息学迁移学习

Transfer learning for materials informatics using crystal graph convolutional neural network

Joohwi Lee, Ryoji Asahi

摘要:

为了成功地将机器学习应用于材料信息学,有必要克服由于数据量不足而导致的预测不准确。在这项研究中,我们提出了一种使用晶体图卷积神经网络(TL-CGCNN)的迁移学习。在本文中,TL-CGCNN使用大数据(例如晶体结构的形成能)进行预训练,然后用于使用相对较小的数据预测目标属性。我们确认TL-CGCNN可以改善对各种性质的预测,如体积模量,介电常数和准粒子带隙,这些性质对计算要求很高,以构建材料的大数据。此外,我们定量地观察到,随着预训练模型中训练数据集大小的增加,通过TL-CGCNN对目标模型中属性的预测变得更加准确。最后,我们确认TL-CGCNN在预测目标属性方面优于其他回归方法,这些方法的数据量较小。因此,我们得出结论,TL-CGCNN很有前途,可以为易于积累且与目标属性相关的材料编制大数据。

英文摘要:

For successful applications of machine learning in materials informatics, it is necessary to overcome the inaccuracy of predictions ascribed to insufficient amount of data. In this study, we propose a transfer learning using a crystal graph convolutional neural network (TL-CGCNN). Herein, TL-CGCNN is pretrained with big data such as formation energies for crystal structures, and then used for predicting target properties with relatively small data. We confirm that TL-CGCNN can improve predictions of various properties such as bulk moduli, dielectric constants, and quasiparticle band gaps, which are computationally demanding, to construct big data for materials. Moreover, we quantitatively observe that the prediction of properties in target models via TL-CGCNN becomes more accurate with an increase in size of training dataset in pretrained models. Finally, we confirm that TL-CGCNN is superior to other regression methods in the predictions of target properties, which suffer from small amount of data. Therefore, we conclude that TL-CGCNN is promising along with compiling big data for materials that are easy to accumulate and relevant to the target properties.

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。

↑