MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation

TL;DR

MolHF introduces a hierarchical flow-based model for molecular graph generation, effectively capturing complex structures and enabling the creation of larger molecules, with state-of-the-art results in generation and property optimization.

Contribution

It is the first flow-based hierarchical model that generates large molecules by addressing the non-differentiability challenge in hierarchical graph generation.

Findings

Achieves state-of-the-art performance in molecular generation and property optimization.

First flow-based model capable of generating large molecules with over 100 heavy atoms.

Demonstrates effective hierarchical generation of complex molecular structures.

Abstract

Molecular de novo design is a critical yet challenging task in scientific fields, aiming to design novel molecular structures with desired property profiles. Significant progress has been made by resorting to generative models for graphs. However, limited attention is paid to hierarchical generative models, which can exploit the inherent hierarchical structure (with rich semantic information) of the molecular graphs and generate complex molecules of larger size that we shall demonstrate to be difficult for most existing models. The primary challenge to hierarchical generation is the non-differentiable issue caused by the generation of intermediate discrete coarsened graph structures. To sidestep this issue, we cast the tricky hierarchical generation problem over discrete spaces as the reverse process of hierarchical representation learning and propose MolHF, a new hierarchical flow-based model that generates molecular graphs in a coarse-to-fine manner. Specifically, MolHF first generates bonds through a multi-scale architecture, then generates atoms based on the coarsened graph structure at each scale. We demonstrate that MolHF achieves state-of-the-art performance in random generation and property optimization, implying its high capacity to model data distribution. Furthermore, MolHF is the first flow-based model that can be applied to model larger molecules (polymer) with more than 100 heavy atoms. The code and models are available at https://github.com/violet-sto/MolHF.