papers AI Learner
The Github is limit! Click to go to the new site.

GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

2019-05-28
Kaushalya Madhawa, Katushiko Ishiguro, Kosuke Nakago, Motoki Abe

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.11600

PDF

http://arxiv.org/pdf/1905.11600


Similar Posts

Comments