Potential Score Matching: Debiasing Molecular Structure Sampling with Potential Energy Guidance
This addresses the problem of efficient and unbiased molecular sampling for physics and chemistry, offering a novel method that is incremental in improving upon existing diffusion models.
The paper tackles the challenge of sampling unbiased molecular conformations by proposing Potential Score Matching (PSM), which uses potential energy gradients to guide generative models, resulting in distributions that more closely approximate the Boltzmann distribution and outperforming SOTA models on the Lennard-Jones potential.
The ensemble average of physical properties of molecules is closely related to the distribution of molecular conformations, and sampling such distributions is a fundamental challenge in physics and chemistry. Traditional methods like molecular dynamics (MD) simulations and Markov chain Monte Carlo (MCMC) sampling are commonly used but can be time-consuming and costly. Recently, diffusion models have emerged as efficient alternatives by learning the distribution of training data. Obtaining an unbiased target distribution is still an expensive task, primarily because it requires satisfying ergodicity. To tackle these challenges, we propose Potential Score Matching (PSM), an approach that utilizes the potential energy gradient to guide generative models. PSM does not require exact energy functions and can debias sample distributions even when trained on limited and biased data. Our method outperforms existing state-of-the-art (SOTA) models on the Lennard-Jones (LJ) potential, a commonly used toy model. Furthermore, we extend the evaluation of PSM to high-dimensional problems using the MD17 and MD22 datasets. The results demonstrate that molecular distributions generated by PSM more closely approximate the Boltzmann distribution compared to traditional diffusion models.