E(n) Equivariant Normalizing Flows

2021/05/19 by Satorras, Victor Garcia, Hoogeboom, Emiel, Fuchs, Fabian B. +2 · 15 citations
#Chemical Physics (physics.chem-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2105.09016

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.

Cited by

• NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
• Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
• Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation
• Flow Autoencoders are Effective Protein Tokenizers
• Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
• MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models
• DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
• Multi-domain Distribution Learning for De Novo Drug Design
• Score Matching on Large Geometric Graphs for Cosmology Generation
• Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation
• Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number
• FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
• Chem3DLLM: 3D Multimodal Large Language Models for Chemistry
• MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning

Related

• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric\n Densities
• Free-form Flows: Make Any Architecture a Normalizing Flow
• Equivariant flow matching
• Equivariant Finite Normalizing Flows
• Modular Flows: Differential Molecular Generation