MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network
This work addresses property prediction in material science, potentially aiding material discovery, but it appears incremental as it combines existing techniques.
The authors tackled property prediction for material discovery by introducing MHG-GNN, an autoencoder combining Graph Neural Networks with Molecular Hypergraph Grammar, and reported promising results on diverse tasks.
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.