GNNs extend the foundational ideas of Convolutional Neural Networks (CNNs) to graph data. While CNNs capture spatial locality in grid-like data (for example, images) through convolutional kernels, ...

We applied three types of established GNN techniques, namely Crystal Graph Convolutional Neural Network (CGCNN), Materials Graph Network (MEGNET), and Atomistic Line Graph Neural Network (ALIGNN), to ...