论文标题
分子在3D中产生的模棱两可的扩散
Equivariant Diffusion for Molecule Generation in 3D
论文作者
论文摘要
这项工作引入了3D分子产生的扩散模型，该模型与欧几里得转化一样。我们的E（3）e术扩散模型（EDM）学会了通过均衡网络的扩散过程来代码，该网络共同在连续（原子坐标）和分类特征（原子类型）上共同运行。此外，我们提供了概率分析，该分析使用我们的模型来承认分子的可能性计算。在实验上，提出的方法显着优于先前的3D分子生成方法，涉及生成的样品质量和训练时效率。
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.
