E(n) Equivariant Normalizing Flows
Machine Learning
2022-01-17 v4 Chemical Physics
Machine Learning
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
@article{arxiv.2105.09016,
title = {E(n) Equivariant Normalizing Flows},
author = {Victor Garcia Satorras and Emiel Hoogeboom and Fabian B. Fuchs and Ingmar Posner and Max Welling},
journal= {arXiv preprint arXiv:2105.09016},
year = {2022}
}
Comments
Accepted at Neural Information Processing Systems (NeurIPS 2021)