GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

Kaushalya Madhawa, Katushiko Ishiguro, Kosuke Nakago, Motoki Abe
5/28/2019
stat.MLcs.AIcs.LG

Official code: chainer/chainer-chemistry (711 stars, MIT, last commit 2023-04-20).

Abstract

We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows. We empirically demonstrate that our model efficiently generates valid molecular graphs with almost no duplicated molecules. In addition, we observe that the learned latent space can be used to generate molecules with desired chemical properties.

View on arXivView PDF

Code Implementations(1)

chainer/chainer-chemistryOfficial100%
MIT

Chainer Chemistry: A Library for Deep Learning in Biology and Chemistry

711132Shell, PythonNov 28, 20173 years agoMIT
biologychainerchemistrydeep-learninggraph-convolutional-networks+2 more

Similar Papers

MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation

87% match1 repo152023

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

85% match2024

Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space

84% match1 repo82024

Hierarchical Bayesian Flow Networks for Molecular Graph Generation

83% match2025

Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation

83% match1 repo382023

Learning Neural Generative Dynamics for Molecular Conformation Generation

83% match2 repos472021

Cite this paper

@article{madhawa2019graphnvp,
  title  = {GraphNVP: An Invertible Flow Model for Generating Molecular Graphs},
  author = {Kaushalya Madhawa and Katushiko Ishiguro and Kosuke Nakago and Motoki Abe},
  year   = {2019},
  eprint = {1905.11600},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1905.11600}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1905.11600.svg)](https://codeofpaper.com/paper/1905.11600)

Discussion