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

2022/05/27 by Jian-Gang Kong, Qingxu Li, Qing-Xu Li +3 · 8 citations
Computer Science · Materials Science · Physics and Astronomy · #Antiferromagnetism #Artificial intelligence #Artificial neural network #Computer science #Condensed matter physics #Convolutional neural network #Graph #Machine Learning in Materials Science #Machine learning #Magnetism #Pattern recognition (psychology) #Physics #Quantum #Theoretical computer science #Topic Modeling #X-ray Diffraction in Crystallography #cond-mat.mtrl-sci #physics.comp-ph

paper · pdf · doi:10.1088/0256-307x/39/6/067503

published in Chinese Physics Letters 39(6), 067503 (Institute of Physics) · 7 pages, 6 figures, 2 tables

arxiv created 2022/05/27 · openalex publication_date 2022/06/01 · openalex created_date 2022/06/12 · arxiv updated 2022/06/13 · openalex updated_date 2026/08/05

Abstract

Antiferromagnetic materials are exciting quantum materials with rich physics and great potential for applications. On 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.

Citations

• Crystal structure representations for machine learning models of formation energies
• Quantum spin liquid states
• SchNet – A deep learning architecture for molecules and materials
• Momentum Contrast for Unsupervised Visual Representation Learning
• Robust axion insulator and Chern insulator phases in a two-dimensional antiferromagnetic topological insulator
• Antiferromagnetic spintronics
• Accuracy of Machine Learning Potential for Predictions of Multiple-Target Physical Properties*
• Learning properties of ordered and disordered materials from multi-fidelity data
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges