Equivariant Diffusion for Molecule Generation in 3D
This work addresses molecule generation for drug discovery or materials science, offering a novel approach with strong performance gains.
The authors tackled the problem of generating 3D molecules by introducing an equivariant diffusion model that is invariant to Euclidean transformations, resulting in significantly outperforming previous methods in sample quality and training efficiency.
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 efficiency at training time.