Equivariant Flow Matching with Hybrid Probability Transport
This work improves molecule generation for computational chemistry and drug discovery, though it appears incremental as it builds on existing diffusion models.
The paper tackles the problem of generating 3D molecules by addressing unstable probability dynamics and slow sampling in diffusion models, achieving better performance on benchmarks with a 4.75× average speedup in sampling.
The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates). Deep generative models, especially Diffusion Models (DMs), have demonstrated effectiveness in generating feature-rich geometries. However, existing DMs typically suffer from unstable probability dynamics with inefficient sampling speed. In this paper, we introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics. More specifically, we propose a hybrid probability path where the coordinates probability path is regularized by an equivariant optimal transport, and the information between different modalities is aligned. Experimentally, the proposed method could consistently achieve better performance on multiple molecule generation benchmarks with 4.75$\times$ speed up of sampling on average.