GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

TL;DR

GraphNVP introduces an invertible flow-based model for molecular graph generation, enabling exact likelihood computation, efficient valid molecule creation, and property-guided molecule synthesis.

Contribution

It is the first invertible flow model specifically designed for molecular graphs, decomposing graph generation into adjacency and node attribute steps with novel reversible flows.

Findings

Efficient generation of valid, unique molecular graphs

Exact likelihood maximization on graph data

Latent space enables property-controlled molecule generation

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.