E(n) Equivariant Normalizing Flows
This enables more accurate generative modeling of molecules and particle systems for applications in chemistry and physics, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of generating 3D molecular structures with Euclidean symmetry by introducing E(n) Equivariant Normalizing Flows, which achieve higher log-likelihoods than baselines on particle systems like DW4 and LJ13 and molecules from QM9.
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.