隐式机器学习力场加速分子动力学模拟

中文摘要 AI 辅助

我们提出隐式机器学习力场（I-MLFFs），用自洽不动点方程替代显式神经网络层堆叠。在分子模拟中，该公式可在连续时间步间复用中间表示，从而对力评估进行热启动。所得模型有效结合了浅层单层MLFF的计算开销与深度神经网络的表示能力和精度。我们的方法实现了架构无关的效率提升，这在单独考虑力预测和轨迹积分时无法获得。我们在三类主要图神经网络架构上验证了这一点：不变型、等变笛卡尔张量型和SO(3)等变球张量型架构，每类都实现了2至5倍的计算和内存开销降低。关键的是，这些增益是在保留全原子分辨率和原始积分时间步长的情况下实现的，避免了空间或时间粗粒化。因此，我们的贡献推进了量子力学精确分子模拟的规模前沿，在固定GPU内存和计算预算内实现了更长的轨迹和更大的原子系统，从而为生物分子和材料系统的新见解打开了大门。

英文摘要

We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations. In molecular simulations, this formulation enables intermediate representations to be reused across successive timesteps, thereby warm-starting force evaluation. The resulting models effectively combine the computational footprint of a shallow, single-layer MLFF with the representational capacity and accuracy of a deep neural network. Our approach unlocks architecture-agnostic efficiency gains that are inaccessible when force prediction and trajectory integration are considered separately. We demonstrate this across three major classes of graph neural networks: invariant, equivariant Cartesian tensor, and SO(3)-equivariant spherical-tensor architectures. Each yields a two- to five-fold reduction in compute and memory footprint. Crucially, these gains are achieved while retaining full atomistic resolution and the original integration timestep, avoiding spatial or temporal coarse graining. Our contribution therefore advances the scaling frontier of quantum-mechanically faithful molecular simulation, enabling longer trajectories and larger atomistic systems within fixed GPU memory and compute budgets, and thereby opening access to new insights across biomolecular and material systems.

发表机构

• Korea University（高丽大学）

机构由 AI 辅助整理，请以论文原文为准。