Score: 2

Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment

Published: June 11, 2025 | arXiv ID: 2506.10186v2

By: Yuhui Ding, Thomas Hofmann

Potential Business Impact:

Makes computers design new molecules faster.

Business Areas:
A/B Testing Data and Analytics

Equivariant diffusion models have achieved impressive performance in 3D molecule generation. These models incorporate Euclidean symmetries of 3D molecules by utilizing an SE(3)-equivariant denoising network. However, specialized equivariant architectures limit the scalability and efficiency of diffusion models. In this paper, we propose an approach that relaxes such equivariance constraints. Specifically, our approach learns a sample-dependent SO(3) transformation for each molecule to construct an aligned latent space. A non-equivariant diffusion model is then trained over the aligned representations. Experimental results demonstrate that our approach performs significantly better than previously reported non-equivariant models. It yields sample quality comparable to state-of-the-art equivariant diffusion models and offers improved training and sampling efficiency. Our code is available at https://github.com/skeletondyh/RADM

Country of Origin
🇨🇭 Switzerland

Repos / Data Links

Page Count
11 pages

Category
Computer Science:
Machine Learning (CS)