Self-Supervised Graph Neural Networks for Accurate Prediction of Néel Temperature

作     者：Jian-Gang Kong Qing-Xu Li Jian Li Yu Liu Jia-Ji Zhu 孔建刚;李清旭;李健;刘羽;朱家骥

作者机构：School of ScienceChongqing University of Posts and TelecommunicationsChongqing 400065China Institute for Advanced SciencesChongqing University of Posts and TelecommunicationsChongqing 400065China Southwest Center for Theoretical PhysicsChongqing UniversityChongqing 401331China Inspur Electronic Information Industry Co.LtdBeijing 100085China 

出 版 物：《Chinese Physics Letters》 (中国物理快报（英文版）)

年 卷 期：2022年第39卷第6期

页      面：5-11页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 070205[理学-凝聚态物理] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0702[理学-物理学] 

基　　金：supported by the Scientific Research Program from Science and Technology Bureau of Chongqing City (Grant No. cstc2020jcyj-msxm X0684) the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant No. KJQN202000639) in part by the National Natural Science Foundation of China (Grant No. 12147102) 

主　　题：utilizing networks neural 

摘      要：Antiferromagnetic materials are exciting quantum materials with rich physics and great potential for *** the other hand, an accurate and efficient theoretical method is highly demanded for determining critical transition temperatures, Néel temperatures, of antiferromagnetic materials. The powerful graph neural networks(GNNs) that succeed in predicting material properties lose their advantage in predicting magnetic properties due to the small dataset of magnetic materials, while conventional machine learning models heavily depend on the quality of material descriptors. We propose a new strategy to extract high-level material representations by utilizing self-supervised training of GNNs on large-scale unlabeled datasets. According to the dimensional reduction analysis, we find that the learned knowledge about elements and magnetism transfers to the generated atomic vector representations. Compared with popular manually constructed descriptors and crystal graph convolutional neural networks, self-supervised material representations can help us to obtain a more accurate and efficient model for Néel temperatures, and the trained model can successfully predict high Néel temperature antiferromagnetic materials. Our self-supervised GNN may serve as a universal pre-training framework for various material properties.