NeurIPS 2024poster8 citations

Equivariant Neural Diffusion for Molecule Generation

François R J Cornet, Grigory Bartosh, Mikkel N. Schmidt, Christian A. Naesseth

Abstract

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.

Diffusion ModelsEquivariant Neural NetworksMolecule Generation
BibTeX
@inproceedings{
cornet2024equivariant,
title={Equivariant Neural Diffusion for Molecule Generation},
author={Fran{\c{c}}ois R J Cornet and Grigory Bartosh and Mikkel N. Schmidt and Christian A. Naesseth},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=40pE5pFhWl}
}