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.

Accepted at Neural Information Processing Systems (NeurIPS 2021)

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• NICE: Non-linear Independent Components Estimation
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• E(n) Equivariant Graph Neural Networks
• High-Dimensional Probability Estimation with Deep Density Models
• Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
• Equivariant Hamiltonian Flows
• Graph Normalizing Flows
• Learning Neural Generative Dynamics for Molecular Conformation Generation

Cited by in corpus (3)

• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Robust Partial-to-Partial Point Cloud Registration in a Full Range
• Optimal Design of Experiments for Simulation-Based Inference of Mechanistic Acyclic Biological Networks