Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks

TL;DR

This paper introduces GeoBFN, a Bayesian flow network model that effectively generates 3D molecular geometries by modeling diverse modalities in a symmetry-invariant, differentiable distribution space, achieving state-of-the-art results.

Contribution

The work presents GeoBFN, a novel probabilistic model that unifies diverse molecular modalities with SE(3) invariance, improving 3D molecule generation quality and efficiency.

Findings

Achieves 90.87% molecule stability on QM9

Attains 85.6% atom stability on GEOM-DRUG

Provides 20-times faster sampling without quality loss

Abstract

Advanced generative model (e.g., diffusion model) derived from simplified continuity assumptions of data distribution, though showing promising progress, has been difficult to apply directly to geometry generation applications due to the multi-modality and noise-sensitive nature of molecule geometry. This work introduces Geometric Bayesian Flow Networks (GeoBFN), which naturally fits molecule geometry by modeling diverse modalities in the differentiable parameter space of distributions. GeoBFN maintains the SE-(3) invariant density modeling property by incorporating equivariant inter-dependency modeling on parameters of distributions and unifying the probabilistic modeling of different modalities. Through optimized training and sampling techniques, we demonstrate that GeoBFN achieves state-of-the-art performance on multiple 3D molecule generation benchmarks in terms of generation quality (90.87% molecule stability in QM9 and 85.6% atom stability in GEOM-DRUG. GeoBFN can also conduct sampling with any number of steps to reach an optimal trade-off between efficiency and quality (e.g., 20-times speedup without sacrificing performance).