MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generation

TL;DR

MolGrow introduces a hierarchical normalizing flow model for molecular graph generation, enabling precise structural modifications and outperforming existing models in distribution learning and property optimization.

Contribution

It presents a novel hierarchical normalizing flow approach for molecular graph generation with invertible operations and controllable structural changes.

Findings

Outperforms existing graph generative models in distribution learning

Enables global and constrained chemical property optimization

Demonstrates precise control over molecular structure modifications

Abstract

We propose a hierarchical normalizing flow model for generating molecular graphs. The model produces new molecular structures from a single-node graph by recursively splitting every node into two. All operations are invertible and can be used as plug-and-play modules. The hierarchical nature of the latent codes allows for precise changes in the resulting graph: perturbations in the top layer cause global structural changes, while perturbations in the consequent layers change the resulting molecule marginally. The proposed model outperforms existing generative graph models on the distribution learning task. We also show successful experiments on global and constrained optimization of chemical properties using latent codes of the model.