E(n) Equivariant Normalizing Flows
Abstract
This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E(n) graph neural networks and integrate them as a differential equation to obtain an invertible equivariant function: a continuous-time normalizing flow. We demonstrate that E-NFs considerably outperform baselines and existing methods from the literature on particle systems such as DW4 and LJ13, and on molecules from QM9 in terms of log-likelihood. To the best of our knowledge, this is the first flow that jointly generates molecule features and positions in 3D.
Cite
Text
Satorras et al. "E(n) Equivariant Normalizing Flows." Neural Information Processing Systems, 2021.Markdown
[Satorras et al. "E(n) Equivariant Normalizing Flows." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/satorras2021neurips-equivariant/)BibTeX
@inproceedings{satorras2021neurips-equivariant,
title = {{E(n) Equivariant Normalizing Flows}},
author = {Satorras, Victor Garcia and Hoogeboom, Emiel and Fuchs, Fabian and Posner, Ingmar and Welling, Max},
booktitle = {Neural Information Processing Systems},
year = {2021},
url = {https://mlanthology.org/neurips/2021/satorras2021neurips-equivariant/}
}