GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

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.

12 pages, 7 figures

Cited by in corpus (7)

• Normalizing Flows: An Introduction and Review of Current Methods
• A Comprehensive Survey on Deep Graph Representation Learning
• Equivariant flow-based sampling for lattice gauge theory
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Controllable Data Generation by Deep Learning: A Review
• Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets
• HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space