提出可学习前向过程的3D分子生成扩散模型，保持空间变换等变性。
Equivariant Neural Diffusion for Molecule Generation
- 设计可学习的前向过程，随时间和数据动态调整变换
- 在标准基准上实现与顶尖模型相当的生成性能
- 适合需要精确3D结构生成的药物研发场景
我们提出等变神经扩散（END），一种用于3D分子生成的新型扩散模型，具有欧几里得变换等变性。与当前最先进的等变扩散模型相比，END的关键创新在于其可学习的前向过程，提升了生成建模能力。前向过程不再是预设的，而是通过时间与数据相关的等变变换参数化。在多个标准分子生成基准上的实验表明，END在无条件和有条件生成任务中均表现优异，达到与多个强基线相当的性能。
原文摘要 · Abstract (English)
We introduce Equivariant Neural Diffusion (END), a novel diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Compared to current state-of-the-art equivariant diffusion models, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。