降低特征相关性可显著提升分子动力学中图神经网络力场的稳定性。
Improving the Stability of GNN Force Field Models by Reducing Feature Correlation
- 通过动态损失系数调度减少边特征相关性，提升模型鲁棒性。
- 在分布外数据上将模拟稳定性从0.03皮秒提升至10皮秒。
- 适用于通用GNNFF训练，计算开销低于3%。
基于图神经网络的力场（GNNFF）模型在半导体材料研究的分子动力学（MD）模拟中广泛应用，虽在训练数据上能量与力的平均绝对误差（MAE）表现优异，但在长时间模拟中面对分布外数据时常出现不稳定问题。本文揭示了特征相关性与模型稳定性之间的负相关关系，提出一种基于特征相关性的改进方法：设计带有动态损失系数调度的损失函数，以减少边特征相关性，该方法可广泛应用于各类GNNFF训练。同时提出一种评估MD模拟稳定性的经验指标。实验表明，该方法能显著提升模型稳定性，尤其在分布外数据场景下，计算开销低于3%。例如，对Allegro模型，模拟稳定时间由0.03皮秒提升至10皮秒。
原文摘要 · Abstract (English)
Recently, Graph Neural Network based Force Field (GNNFF) models are widely used in Molecular Dynamics (MD) simulation, which is one of the most cost-effective means in semiconductor material research. However, even such models provide high accuracy in energy and force Mean Absolute Error (MAE) over trained (in-distribution) datasets, they often become unstable during long-time MD simulation when used for out-of-distribution datasets. In this paper, we propose a feature correlation based method for GNNFF models to enhance the stability of MD simulation. We reveal the negative relationship between feature correlation and the stability of GNNFF models, and design a loss function with a dynamic loss coefficient scheduler to reduce edge feature correlation that can be applied in general GNNFF training. We also propose an empirical metric to evaluate the stability in MD simulation. Experiments show our method can significantly improve stability for GNNFF models especially in out-of-distribution data with less than 3% computational overhead. For example, we can ensure the stable MD simulation time from 0.03ps to 10ps for Allegro model.
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。