Skip to yearly menu bar Skip to main content


Poster

Equivariant Neural Diffusion for Molecule Generation

François Cornet · Grigory Bartosh · Mikkel Schmidt · Christian Andersson Naesseth

East Exhibit Hall A-C #2403
[ ]
Thu 12 Dec 11 a.m. PST — 2 p.m. PST

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.

Chat is not available.