Equivariant Neural Diffusion for Molecule Generation
This work addresses molecule generation for computational chemistry, but it is incremental as it builds on existing equivariant diffusion models with a novel forward process.
The paper tackled molecule generation in 3D by introducing Equivariant Neural Diffusion (END), a diffusion model with a learnable forward process that is equivariant to Euclidean transformations, and demonstrated competitive performance on standard benchmarks.
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.