MCGM让分子图网络高效捕捉远距离相互作用，提升精度且不增加太多计算量。
MCGM: Multi-stage Clustered Global Modeling for Long-range Interactions in Molecules
- 分层聚类构建多尺度原子簇，动态提取全局信息
- 在多个数据集上平均降低26.2%能量预测误差，达到17.0 meV能量精度
- 轻量插件设计，适合各类几何图神经网络，适合需高精度的分子模拟任务
几何图神经网络擅长捕捉分子结构，但其局部消息传递机制难以建模长程相互作用。现有方法存在根本局限：扩展截断半径导致计算开销随距离呈立方增长；物理启发核函数（如库仑、色散）常具系统特异性且缺乏通用性；傅里叶空间方法需精细调参（如网格大小、k空间截断），增加计算负担。本文提出多阶段聚类全局建模（MCGM），一种轻量级、可即插即用的模块，通过高效聚类操作为几何图神经网络注入层次化全局上下文。MCGM构建原子簇的多分辨率层次结构，通过动态分层聚类提炼全局信息，并经学习变换反向传播，最终通过残差连接增强原子特征。无缝集成于四种不同主干架构，在OE62上平均降低26.2%能量预测误差；在AQM数据集上实现17.0 meV能量精度和4.9 meV/Å力精度，参数量比Neural P3M少20%。代码将在接受后公开。
原文摘要 · Abstract (English)
Geometric graph neural networks (GNNs) excel at capturing molecular geometry, yet their locality-biased message passing hampers the modeling of long-range interactions. Current solutions have fundamental limitations: extending cutoff radii causes computational costs to scale cubically with distance; physics-inspired kernels (e.g., Coulomb, dispersion) are often system-specific and lack generality; Fourier-space methods require careful tuning of multiple parameters (e.g., mesh size, k-space cutoff) with added computational overhead. We introduce Multi-stage Clustered Global Modeling (MCGM), a lightweight, plug-and-play module that endows geometric GNNs with hierarchical global context through efficient clustering operations. MCGM builds a multi-resolution hierarchy of atomic clusters, distills global information via dynamic hierarchical clustering, and propagates this context back through learned transformations, ultimately reinforcing atomic features via residual connections. Seamlessly integrated into four diverse backbone architectures, MCGM reduces OE62 energy prediction error by an average of 26.2%. On AQM, MCGM achieves state-of-the-art accuracy (17.0 meV for energy, 4.9 meV/Å for forces) while using 20% fewer parameters than Neural P3M. Code will be made available upon acceptance.
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。