论文标题
使用Crystal Graph卷积神经网络的材料信息传输学习
Transfer learning for materials informatics using crystal graph convolutional neural network
论文作者
论文摘要
为了成功地应用机器学习在材料信息学中，有必要克服归因于不足数据的预测的不准确性。在这项研究中，我们建议使用晶体图卷积神经网络（TL-CGCNN）进行转移学习。本文中，TL-CGCNN经过大数据进行了鉴定，例如用于晶体结构的形成能，然后用于预测具有相对较小数据的目标性质。我们确认，TL-CGCNN可以改善各种特性的预测，例如散装模量，介电常数和准粒子带隙，这些质量在计算上要求，以构建材料的大数据。此外，我们定量地观察到，随着预审预周化模型中训练数据集的大小增加，通过TL-CGCNN在目标模型中的性质预测变得更加准确。最后，我们确认TL-CGCNN在目标特性的预测中优于其他数据，这些方法遭受了少量数据。因此，我们得出的结论是，TL-CGCNN有希望，并为易于积累且与目标特性相关的材料编译大数据。
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.
