Graph Energy-Based Model for Molecular Graph Generation
Abstract
We present Graph Energy-based Model (GEM), an energy-based model for molecular graph generation. GEM uses dequantization and gradient symmetrization to incorporate generation by stochastic gradient Langevin dynamics for graph representation that is discrete and includes symmetric constraint. Experimental results show that \gem can comparably design compounds as other deep generative approaches.
Cite
Text
Hataya et al. "Graph Energy-Based Model for Molecular Graph Generation." ICLR 2021 Workshops: EBM, 2021.Markdown
[Hataya et al. "Graph Energy-Based Model for Molecular Graph Generation." ICLR 2021 Workshops: EBM, 2021.](https://mlanthology.org/iclrw/2021/hataya2021iclrw-graph/)BibTeX
@inproceedings{hataya2021iclrw-graph,
title = {{Graph Energy-Based Model for Molecular Graph Generation}},
author = {Hataya, Ryuichiro and Nakayama, Hideki and Yoshizoe, Kazuki},
booktitle = {ICLR 2021 Workshops: EBM},
year = {2021},
url = {https://mlanthology.org/iclrw/2021/hataya2021iclrw-graph/}
}