E(n) Equivariant Normalizing FlowsDownload PDF

21 May 2021, 20:44 (modified: 26 Oct 2021, 12:05)NeurIPS 2021 OralReaders: Everyone
Keywords: equivariance, normalizing flows, molecule generation, generative models, graph neural networks
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.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: https://github.com/vgsatorras/en_flows
9 Replies