Equivariant Neural Diffusion for Molecule Generation

TL;DR

This paper presents Equivariant Neural Diffusion (END), a new 3D molecule generation model that is equivariant to Euclidean transformations, featuring a learnable forward process for improved generative performance.

Contribution

The paper introduces a learnable, equivariant forward process in a diffusion model for 3D molecule generation, advancing beyond fixed processes used in prior models.

Findings

END achieves competitive results on standard benchmarks.

The learnable forward process enhances generative quality.

END performs well in both unconditional and conditional generation.

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.