Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment

About

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

Yuhui Ding, Thomas Hofmann• 2025

Related benchmarks

TaskDatasetResultRank
3D Molecule GenerationQM9 unconditional generation
Atom Stability98.5
42
Conditional 3D Molecule GenerationQM9
Dipole Moment µ (D)0.814
16
Unconditional 3D Molecular GenerationGEOM Drugs
Atom Stability85
7
Showing 3 of 3 rows

Other info

Follow for update