mhg-gnn
MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network
Kishimoto, Akihiro, Kajino, Hiroshi, Hirose, Masataka, Fuchiwaki, Junta, Priyadarsini, Indra, Hamada, Lisa, Shinohara, Hajime, Nakano, Daiju, Takeda, Seiji
Property prediction plays an important role in material discovery. As an initial step to eventually develop a foundation model for material science, we introduce a new autoencoder called the MHG-GNN, which combines graph neural network (GNN) with Molecular Hypergraph Grammar (MHG). Results on a variety of property prediction tasks with diverse materials show that MHG-GNN is promising.
2309.16374
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.95)