paper-with-me

홈 › Papers

SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

2024-10-08 · Leo Zhang, Kianoosh Ashouritaklimi, Yee Whye Teh, Rob Cornish

We propose SymDiff, a novel method for constructing equivariant diffusion models using the recently introduced 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. Notably, in contrast to previous work, SymDiff typically does not require any neural network components that are intrinsically equivariant, avoiding the need for complex parameterizations and 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 on $\mathrm{E}(3)$-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.

📄 PDF Abstract BibTeX arXiv:2410.06262

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Stochastic Neural Network Symmetrisation in Markov Categories

2024-06-17 · Rob Cornish

We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $\varphi : H \to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-equivariant on…

Asymmetric Diffusion Recommendation Model

2025-08-18 · Yongchun Zhu, Guanyu Jiang, Jingwu Chen, Feng Zhang 외 arxiv

Recently, motivated by the outstanding achievements of diffusion models, the diffusion process has been employed to strengthen representation learning in recommendation systems. Most diffusion-based recommendation models…

Representation LearningRecommendation Systems

Neural Network Symmetrisation in Concrete Settings

2024-12-12 · Rob Cornish

Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implications for the symmetr…

Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation

2023-09-06 · CVPR 2024 1 · Hyunwoo Ryu, Jiwoo Kim, Hyunseok An, Junwoo Chang 외

Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-ba…

DenoisingTranslation

Equivariant Neural Diffusion for Molecule Generation

2025-06-12 · François Cornet, Grigory Bartosh, Mikkel N. Schmidt, Christian A. Naesseth

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, …