通过学习规范姿态，提升对称分布生成质量与速度
Symmetry-Aware Generative Modeling through Learned Canonicalization
- 用等变网络将样本映射到标准姿态，只学每轨道一个代表
- 在分子建模上样本质量更高，推理速度更快
- 适合需高效生成对称结构的科学计算场景
对称分布的生成建模在药物发现、物理模拟等科学领域有广泛应用。现有方法采用不变先验结合等变生成过程，但存在局限性。本文提出新思路：学习密度的一个可学习切片，仅保留每个轨道的一个代表性样本。为此，设计一个群等变的规范化网络，将训练样本映射到规范姿态，并在此基础上训练非等变生成模型。该方法应用于扩散模型，在分子建模的初步实验中表现优异，样本质量更优，推理速度更快。
原文摘要 · Abstract (English)
Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing generative modeling paradigm for invariant densities combines an invariant prior with an equivariant generative process. However, we observe that this technique is not necessary and has several drawbacks resulting from the limitations of equivariant networks. Instead, we propose to model a learned slice of the density so that only one representative element per orbit is learned. To accomplish this, we learn a group-equivariant canonicalization network that maps training samples to a canonical pose and train a non-equivariant generative model over these canonicalized samples. We implement this idea in the context of diffusion models. Our preliminary experimental results on molecular modeling are promising, demonstrating improved sample quality and faster inference time.
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。