Equivariant Neural Diffusion for Molecule Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cornet, François, Bartosh, Grigory, Schmidt, Mikkel N., Naesseth, Christian A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916791915118592
author Cornet, François
Bartosh, Grigory
Schmidt, Mikkel N.
Naesseth, Christian A.
author_facet Cornet, François
Bartosh, Grigory
Schmidt, Mikkel N.
Naesseth, Christian A.
contents 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, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10532
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Equivariant Neural Diffusion for Molecule Generation
Cornet, François
Bartosh, Grigory
Schmidt, Mikkel N.
Naesseth, Christian A.
Machine Learning
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, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.
title Equivariant Neural Diffusion for Molecule Generation
topic Machine Learning
url https://arxiv.org/abs/2506.10532