Accelerating 3D Molecule Generative Models with Trajectory Diagnosis

Zhilong Zhang, Yuxuan Song, Yichun Wang, Jingjing Gong, Hanlin Wu, Dongzhan Zhou, Hao Zhou, Wei-Ying Ma

Keywords: 3D Molecule Generation, Fast Generation, Drug Design

TL;DR: A novel method for fast 3D molecule generation

Abstract: Geometric molecule generative models have found expanding applications across various scientific domains, but their generation inefficiency has become a critical bottleneck. Through a systematic investigation of the generative trajectory, we discover a unique challenge for molecule geometric graph generation: generative models require determining the permutation order of atoms in the molecule before refining its atomic feature values. Based on this insight, we decompose the generation process into permutation phase and adjustment phase, and propose a geometric-informed prior and consistency parameter objective to accelerate each phase. Extensive experiments demonstrate that our approach achieves competitive performance with approximately 10 sampling steps, 7.5 × faster than previous state-of-the-art models and approximately 100 × faster than diffusion-based models, offering a significant step towards scalable molecular generation.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 14158