Predicting Magnetic Properties of van der Waals Magnets Using Graph Neural Networks

We present a study of van der Waals (vdW) magnetic materials using state-of-the-art machine learning models that leverage graph theory. Using a graph-theoretic representation for materials allows us to better learn structure-property relationships by leveraging both the chemical properties of the constituent atoms and the connectivity between those atoms. Graph neural network models can predict both the global properties of a crystal structure and the local properties of the constituent atoms. We embed physical constraints into our model by simultaneously making predictions of local and global properties. In particular, we use the Atomistic Line Graph Neural Network (ALIGNN) architecture. We train the ALIGNN model on data comprising local and global magnetic moments of 314 vdW monolayer structures of the form CrAⁱⁱBⁱBⁱⁱX₆, based on monolayer Cr₂Ge₂Te₆, calculated from first-principles. By learning the relationships between both local and global magnetic properties, we demonstrate an improvement over models that only consider global magnetic properties.