ModelMatErials Graph Network
MEGNet
A graph-network-based model for predicting material properties that can simultaneously handle molecules and crystal structures and predict multiple properties.
Timeline (last 90 days)
Oct 18
Graph neural networks (GNN) treat crystal structures as graphs and aggregate neighbor information through message passing to predict properties such as formation energy, band gap and elastic modulus, with typical models including CGCNN, SchNet, MEGNet and ALIGNN.
Unverified50%