Alex Kutana, Koji Shimizu, Satoshi Watanabe, Ryoji Asahi
{"title":"用等变图卷积神经网络表示玻恩有效电荷","authors":"Alex Kutana, Koji Shimizu, Satoshi Watanabe, Ryoji Asahi","doi":"arxiv-2409.08940","DOIUrl":null,"url":null,"abstract":"Graph convolutional neural networks have been instrumental in machine\nlearning of material properties. When representing tensorial properties,\nweights and descriptors of a physics-informed network must obey certain\ntransformation rules to ensure the independence of the property on the choice\nof the reference frame. Here we explicitly encode such properties using an\nequivariant graph convolutional neural network. The network respects rotational\nsymmetries of the crystal throughout by using equivariant weights and\ndescriptors and provides a tensorial output of the target value. Applications\nto tensors of atomic Born effective charges in diverse materials including\nperovskite oxides, Li3PO4, and ZrO2, are demonstrated, and good performance and\ngeneralization ability is obtained.","PeriodicalId":501234,"journal":{"name":"arXiv - PHYS - Materials Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Representing Born effective charges with equivariant graph convolutional neural networks\",\"authors\":\"Alex Kutana, Koji Shimizu, Satoshi Watanabe, Ryoji Asahi\",\"doi\":\"arxiv-2409.08940\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Graph convolutional neural networks have been instrumental in machine\\nlearning of material properties. When representing tensorial properties,\\nweights and descriptors of a physics-informed network must obey certain\\ntransformation rules to ensure the independence of the property on the choice\\nof the reference frame. Here we explicitly encode such properties using an\\nequivariant graph convolutional neural network. The network respects rotational\\nsymmetries of the crystal throughout by using equivariant weights and\\ndescriptors and provides a tensorial output of the target value. Applications\\nto tensors of atomic Born effective charges in diverse materials including\\nperovskite oxides, Li3PO4, and ZrO2, are demonstrated, and good performance and\\ngeneralization ability is obtained.\",\"PeriodicalId\":501234,\"journal\":{\"name\":\"arXiv - PHYS - Materials Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Materials Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08940\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Materials Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08940","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Representing Born effective charges with equivariant graph convolutional neural networks
Graph convolutional neural networks have been instrumental in machine
learning of material properties. When representing tensorial properties,
weights and descriptors of a physics-informed network must obey certain
transformation rules to ensure the independence of the property on the choice
of the reference frame. Here we explicitly encode such properties using an
equivariant graph convolutional neural network. The network respects rotational
symmetries of the crystal throughout by using equivariant weights and
descriptors and provides a tensorial output of the target value. Applications
to tensors of atomic Born effective charges in diverse materials including
perovskite oxides, Li3PO4, and ZrO2, are demonstrated, and good performance and
generalization ability is obtained.