Equivariant Diffusion for Molecule Generation in 3D. (arXiv:2203.17003v2 [cs.LG] UPDATED)

This work introduces a diffusion model for molecule generation in 3D that is
equivariant to Euclidean transformations. Our E(3) Equivariant Diffusion Model
(EDM) learns to denoise a diffusion process with an equivariant network that
jointly operates on both continuous (atom coordinates) and categorical features
(atom types). In addition, we provide a probabilistic analysis which admits
likelihood computation of molecules using our model. Experimentally, the
proposed method significantly outperforms previous 3D molecular generative
methods regarding the quality of generated samples and …

3d arxiv diffusion generation lg