Self-supervised graph neural networks for accurate prediction of N\'{e}el temperature

TL;DR

This paper introduces a self-supervised graph neural network approach that leverages large unlabeled datasets to accurately predict Ne9el temperatures in antiferromagnetic materials, outperforming traditional methods.

Contribution

It proposes a novel self-supervised training strategy for GNNs to improve magnetic property predictions, especially with limited labeled data.

Findings

Self-supervised GNN learns transferable knowledge about elements and magnetism.

The model achieves higher accuracy in predicting Ne9el temperatures.

The approach outperforms traditional descriptors and supervised GNNs.

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.