Self-supervised graph neural networks for accurate prediction of N\'{e}el 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, N\'{e}el 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 N\'{e}el temperatures, and the trained model can successfully predict high N\'{e}el temperature antiferromagnetic materials. Our self-supervised GNN may serve as a universal pre-training framework for various material properties.