Modular Flows: Differential Molecular Generation

Vikas Garg, Markus Heinonen, Samuel Kaski, Yogesh Verma

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

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 the encoding and the decoding steps that necessitates post hoc validity correction. We circumvent these issues with novel continuous normalizing E(3)-equivariant flows, based on a system of node ODEs coupled as a graph PDE, that repeatedly reconcile locally toward globally aligned densities. Our models can be cast as message-passing temporal networks, and result in superlative performance on the tasks of density estimation and molecular generation. In particular, our generated samples achieve state-of-the-art on both the standard QM9 and ZINC250K benchmarks.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 35
Subtitle of host publication36th Conference on Neural Information Processing Systems (NeurIPS 2022)
EditorsS. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
Place of PublicationRed Hook, NY
PublisherCurran Associates, Inc.
Pages12409-12421
Number of pages13
Volume17
ISBN (Electronic)9781713873129
ISBN (Print)9781713871088
Publication statusPublished - Apr 2023
EventConference on Neural Information Processing Systems -
Duration: 28 Nov 20229 Dec 2022

Conference

ConferenceConference on Neural Information Processing Systems
Period28/11/229/12/22

Keywords

  • machine learning
  • biomolecules

Research Beacons, Institutes and Platforms

  • Institute for Data Science and AI
  • Digital Futures
  • Sustainable Futures

Fingerprint

Dive into the research topics of 'Modular Flows: Differential Molecular Generation'. Together they form a unique fingerprint.

Cite this