[2203.17003] Equivariant Diffusion for Molecule Generation in 3D

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.

Equivariant Diffusion for Molecule Generation in 3D Emiel Hoogeboom * 1 Victor Garcia Satorras * 1 Clément Vignac * 2 Max Welling 1 Abstract This work introduces a diffusion model for molecule generation in 3D that is equivariant to arXiv:2203.17003v2 [cs.LG] 16 Jun 2022 Euclidean transformations. Our E(3) Equivariant…

related reading

• What are Diffusion Models? | Lil'Loglilianweng.github.io
• What are Diffusion Models?lilianweng.github.io
• Diffusion model - Wikipediaen.wikipedia.org
• ⭐️ Diffusion Modelsandrewkchan.dev
• Modeling Symmetries | Mark Neumannmarkneumann.xyz
• Diffusion models from scratchchenyang.co
• 2409.02908arxiv.org
• Energy-Based Modelsenergy-based-model.github.io
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• Step-by-Step Diffusion: An Elementary Tutorialarxiv.org
• https://arxiv.org/pdf/2006.11239arxiv.org
• [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org