Keywords: normalizing flow, molecule generation, graph neural networks, neural ode
TL;DR: We propose generative graph normalizing flow models, based on PDEs, for high quality molecular generation
Abstract: Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis. Flows can generate molecules effectively by inverting the encoding process, however, existing flow models either require artifactual dequantization or specific node/edge orderings, lack desiderata such as permutation invariance, or induce discrepancy between encoding and decoding steps that necessitates post hoc validity correction. Inspired by graph PDEs, we circumvent these issues with novel continuous normalizing E(3)-equivariant flows, based on a system of coupled node ODEs, that repeatedly reconcile locally toward globally aligned densities. Our models can be cast as message passing temporal networks, and result in superlative density estimation and molecular generation. In particular, our generated samples achieve state of the art on both the standard QM9 and ZINC250K benchmarks.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/modular-flows-differential-molecular/code)
23 Replies
Loading