arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.06262cs.LGstat.ML
收藏

SymDiff:基于随机对称化的等变扩散

SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

University of Oxford(牛津大学)

Leo Zhang, Kianoosh Ashouritaklimi, Yee Whye Teh, Rob Cornish

AI总结:

提出SymDiff,通过随机对称化框架构建等变扩散模型,无需内在等变神经网络组件,在E(3)-等变分子生成中取得显著实证收益。

摘要:

我们提出了SymDiff,一种利用随机对称化框架构建等变扩散模型的方法。SymDiff类似于在采样时部署的学习型数据增强,它轻量、计算高效,且易于在任意现成模型上实现。与以往工作不同,SymDiff通常不需要任何内在等变的神经网络组件,从而避免了复杂参数化或使用高阶几何特征的需要。相反,我们的方法可以利用高度可扩展的现代架构作为这些受限替代方案的直接替代品。我们证明了这种额外的灵活性为E(3)-等变分子生成带来了显著的实证收益。据我们所知,这是对称化在生成建模中的首次应用,表明其在该领域更广泛的潜力。

英文摘要:

We propose SymDiff, a method for constructing equivariant diffusion models using the framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is deployed at sampling time, and is lightweight, computationally efficient, and easy to implement on top of arbitrary off-the-shelf models. In contrast to previous work, SymDiff typically does not require any neural network components that are intrinsically equivariant, avoiding the need for complex parameterisations or the use of higher-order geometric features. Instead, our method can leverage highly scalable modern architectures as drop-in replacements for these more constrained alternatives. We show that this additional flexibility yields significant empirical benefit for $\mathrm{E}(3)$-equivariant molecular generation. To the best of our knowledge, this is the first application of symmetrisation to generative modelling, suggesting its potential in this domain more generally.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑