缓解基于分数的分子构象生成中的暴露偏差
Mitigating Exposure Bias in Score-Based Generation of Molecular Conformations
AI总结：
本文针对分子构象生成中SGMs的暴露偏差问题，提出了测量方法并设计了补偿算法Input Perturbation (IP)，显著提升了基于SGM的模型生成构象的准确性与多样性，并在GEOM-Drugs数据集上达到新SOTA。
摘要：
分子构象生成在计算化学领域提出了一个重大挑战。最近，Diffusion Probabilistic Models (DPMs) 和 Score-Based Generative Models (SGMs) 因其能够生成远超传统基于物理方法的准确构象的能力而被有效使用。然而，训练与推理之间的差异引发了一个被称为暴露偏差的关键问题。虽然这个问题在 DPMs 中已被广泛研究，但 SGMs 中暴露偏差的存在及其有效测量仍未解决，这阻碍了用于 SGMs 的补偿方法的使用，包括以 ConfGF 和 Torsional Diffusion 为代表。在这项工作中，我们首先提出了一种用于测量分子构象生成中 SGMs 暴露偏差的方法，这证实了这些模型中暴露偏差的显著存在并测量了其值。我们设计了一种新的补偿算法 Input Perturbation (IP)，它改编自一种最初仅为 DPMs 设计的方法。实验结果表明，通过引入 IP，基于 SGM 的分子构象模型可以显著提高生成构象的准确性和多样性。特别是通过使用 IP 增强的 Torsional Diffusion 模型，我们在 GEOM-Drugs 数据集上实现了新的最先进性能，并在 GEOM-QM9 上表现持平。我们在 https://github.com/jia-975/torsionalDiff-ip 上公开提供了代码。
英文摘要：
Molecular conformation generation poses a significant challenge in the field of computational chemistry. Recently, Diffusion Probabilistic Models (DPMs) and Score-Based Generative Models (SGMs) are effectively used due to their capacity for generating accurate conformations far beyond conventional physics-based approaches. However, the discrepancy between training and inference rises a critical problem known as the exposure bias. While this issue has been extensively investigated in DPMs, the existence of exposure bias in SGMs and its effective measurement remain unsolved, which hinders the use of compensation methods for SGMs, including ConfGF and Torsional Diffusion as the representatives. In this work, we first propose a method for measuring exposure bias in SGMs used for molecular conformation generation, which confirms the significant existence of exposure bias in these models and measures its value. We design a new compensation algorithm Input Perturbation (IP), which is adapted from a method originally designed for DPMs only. Experimental results show that by introducing IP, SGM-based molecular conformation models can significantly improve both the accuracy and diversity of the generated conformations. Especially by using the IP-enhanced Torsional Diffusion model, we achieve new state-of-the-art performance on the GEOM-Drugs dataset and are on par on GEOM-QM9. We provide the code publicly at https://github.com/jia-975/torsionalDiff-ip.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
