Self-supervised graph neural networks for accurate prediction of Néel temperature

Abstract

Antiferromagnetic materials are exciting quantum materials with rich physics and great potential for applications. It is highly demanded of the accurate and efficient theoretical method for determining the critical transition temperatures, Néel temperatures, of antiferromagnetic materials. The powerful graph neural networks (GNN) 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 GNN 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 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.

arXiv comment7 pages, 6 figures, 2 tables

References in corpus (30)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Antiferromagnetic spintronics
• Antiferromagnetic spintronics
• SchNet - a deep learning architecture for molecules and materials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Electrical switching of an antiferromagnet
• Quantum Spin Liquid States
• Momentum Contrast for Unsupervised Visual Representation Learning
• Big Data of Materials Science - Critical Role of the Descriptor
• Robust axion insulator and Chern insulator phases in a two-dimensional antiferromagnetic topological insulator
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Quantum Anomalous Hall Effect in Graphene Proximity Coupled to an Antiferromagnetic Insulator
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Learning Properties of Ordered and Disordered Materials from Multi-fidelity Data
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Spin colossal magnetoresistance in an antiferromagnetic insulator
• k=0 magnetic structure and absence of ferroelectricity in SmFeO3
• Projected Entangled Pair States at Finite Temperature: Imaginary Time Evolution with Ancillas
• Predicting the Curie temperature of ferromagnets using machine learning
• Linearized Tensor Renormalization Group Algorithm for Thermodynamics of Quantum Lattice Models
• Transfer learning for materials informatics using crystal graph convolutional neural network
• Antiferromagnetism at T > 500 K in the Layered Hexagonal Ruthenate SrRu2O6
• An accelerating approach of designing ferromagnetic materials via machine learning modeling of magnetic ground state and Curie temperature
• Few-shot machine learning in the three-dimensional Ising model
• The origin of exchange bias in multigranular non-collinear IrMn${}_3$/CoFe thin films
• Finite-temperature symmetric tensor network for spin-1/2 Heisenberg antiferromagnets on the square lattice
• Atomistic graph networks for experimental materials property prediction
• Network-Initialized Monte Carlo Based on Generative Neural Networks