动态截断让分子模拟更快更省内存，精度几乎不变。
Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials
- 用可变截断半径替代固定半径，按需只算邻近原子。
- 在4种顶尖模型上实现2.26倍省内存、2.04倍提速。
- 适合大规模分子动力学模拟，尤其关注效率的科研人员。
机器学习势函数（MLIPs）在分子动力学模拟中已广泛应用，助力药物与材料发现。然而，其在真实尺度模拟中面临推理速度慢和内存消耗大的主要瓶颈。本文挑战了截断半径必须恒定的传统观念，首次提出动态截断方法，在保证长时间模拟稳定性的前提下，通过设定每原子固定邻居数来诱导原子图稀疏化，显著降低内存占用与推理时间。我们在4个前沿模型（MACE、Nequip、Orbv3、TensorNet）上实现该方法，平均减少2.26倍内存消耗，推理速度提升2.04倍，具体效果因模型和体系而异。误差分析显示，动态截断模型在材料与分子数据集上相比固定截断版本精度损失极小。所有模型实现与训练代码将开源。
原文摘要 · Abstract (English)
Machine learning interatomic potentials (MLIPs) have proven to be wildly useful for molecular dynamics simulations, powering countless drug and materials discovery applications. However, MLIPs face two primary bottlenecks preventing them from reaching realistic simulation scales: inference time and memory consumption. In this work, we address both issues by challenging the long-held belief that the cutoff radius for the MLIP must be held to a fixed, constant value. For the first time, we introduce a dynamic cutoff formulation that still leads to stable, long timescale molecular dynamics simulation. In introducing the dynamic cutoff, we are able to induce sparsity onto the underlying atom graph by targeting a specific number of neighbors per atom, significantly reducing both memory consumption and inference time. We show the effectiveness of a dynamic cutoff by implementing it onto 4 state of the art MLIPs: MACE, Nequip, Orbv3, and TensorNet, leading to 2.26x less memory consumption and 2.04x faster inference time, depending on the model and atomic system. We also perform an extensive error analysis and find that the dynamic cutoff models exhibit minimal accuracy dropoff compared to their fixed cutoff counterparts on both materials and molecular datasets. All model implementations and training code will be fully open sourced.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。