Straight-Line Diffusion Model for Efficient 3D Molecular Generation
Tsinghua University; Chinese Academy of Sciences · Tsinghua University, Tsinghua University · Tsinghua University · Huazhong University of Science and Technology · Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Chinese Academy of Sciences · Institute for AI Industry Research (AIR), Tsinghua University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.