Straight-Line Diffusion Model for Efficient 3D Molecular Generation
By: Yuyan Ni , Shikun Feng , Haohan Chi and more
Potential Business Impact:
Makes computers design new molecules 100 times faster.
Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem, by formulating the diffusion process to follow a linear trajectory. The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process, thus enhancing learning efficiency and efficacy. Consequently, SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency.
Similar Papers
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
Machine Learning (CS)
Makes computers design new molecules faster.
Equivariant Neural Diffusion for Molecule Generation
Machine Learning (CS)
Builds new molecules that fit perfectly.
DMol: A Schedule-Driven Diffusion Model for Highly Efficient and Versatile Molecule Generation
Machine Learning (CS)
Creates new medicines faster and better.