Deep Multi-View Spatiotemporal Virtual Graph Neural Network . . . To address these limitations, we propose a new virtual graph modeling method to focus on significant demand regions and a novel Deep Multi-View Spatiotemporal Virtual Graph Neural Network (DMVST-VGNN) to strengthen learning capabilities of spatial dynamics and temporal long-term dependencies
Virtual Node Graph Neural Network for Full Phonon Prediction This repository provides the implementation of the Virtual Node Graph Neural Network (VGNN) for full phonon prediction in materials science VGNN is designed to address the challenges in phonon prediction using graph neural networks
Virtual node graph neural network for full phonon prediction Our proposed VGNN approach offers a versatile framework for predicting material properties with variable dimensions, a capability we have demonstrated through phonon predictions in this study