通过引入网格点增强几何GNN，提升大分子长程相互作用建模能力。
Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
- 在原子基础上加入可学习的网格点，重构数学运算机制。
- 在MD22和OE62数据集上能量与力预测精度显著提升，平均增益22%。
- 适配多种架构，适用于复杂分子系统的高精度模拟。
几何图神经网络（GNN）在分子几何建模中表现出强大能力，但在大分子系统中难以有效捕捉长程相互作用。为解决这一问题，我们提出Neural P$^3$M，一种可扩展的几何GNN增强器，通过在原子之外引入网格点，并将传统数学操作以可训练方式重新定义，从而扩展其建模能力。Neural P$^3$M在多种分子系统中展现良好适应性，在能量和力预测任务上表现优异，优于多个基准模型，尤其在MD22数据集上表现突出；在OE62数据集上实现平均22%的性能提升，且能无缝集成到多种现有架构中。
原文摘要 · Abstract (English)
Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems. To address this challenge, we introduce Neural P$^3$M, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P$^3$M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures.
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。