ML Anthology

MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network

Akihiro Kishimoto, Hiroshi Kajino, Hirose Masataka, Junta Fuchiwaki, Indra Priyadarsini, Lisa Hamada, Hajime Shinohara, Daiju Nakano, Seiji Takeda
NeurIPSW 2023
/neuripsw/2023/kishimoto2023neuripsw-mhggnn/

Abstract

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.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Kishimoto et al. "MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network." NeurIPS 2023 Workshops: AI4Mat, 2023.

Markdown

[Kishimoto et al. "MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network." NeurIPS 2023 Workshops: AI4Mat, 2023.](https://mlanthology.org/neuripsw/2023/kishimoto2023neuripsw-mhggnn/)

BibTeX

@inproceedings{kishimoto2023neuripsw-mhggnn,
  title     = {{MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network}},
  author    = {Kishimoto, Akihiro and Kajino, Hiroshi and Masataka, Hirose and Fuchiwaki, Junta and Priyadarsini, Indra and Hamada, Lisa and Shinohara, Hajime and Nakano, Daiju and Takeda, Seiji},
  booktitle = {NeurIPS 2023 Workshops: AI4Mat},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/kishimoto2023neuripsw-mhggnn/}
}