Saved in:
Bibliographic Details
Main Authors: Zhang, Leo, Ashouritaklimi, Kianoosh, Teh, Yee Whye, Cornish, Rob
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.06262
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929737197158400
author Zhang, Leo
Ashouritaklimi, Kianoosh
Teh, Yee Whye
Cornish, Rob
author_facet Zhang, Leo
Ashouritaklimi, Kianoosh
Teh, Yee Whye
Cornish, Rob
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06262
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
Zhang, Leo
Ashouritaklimi, Kianoosh
Teh, Yee Whye
Cornish, Rob
Machine Learning
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.
title SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
topic Machine Learning
url https://arxiv.org/abs/2410.06262