用单纯形结构建模复杂时空关系，提升精度与效率
Modern Structure-Aware Simplicial Spatiotemporal Neural Network
- 基于高维单纯形结构设计时空随机游走机制
- 可捕捉高阶拓扑关系，计算开销低于传统图模型
- 适合处理具有复杂关联的大规模时空数据
时空建模已从简单时间序列分析发展为结构化时间序列分析的核心。尽管现有研究广泛使用图神经网络（GNN）进行空间特征提取并取得显著成效，但其仅能捕获成对关系，难以表达真实世界网络中丰富的拓扑结构。同时，基于GNN的模型随图复杂度增加而面临严重计算瓶颈，限制了在大规模网络中的应用。为此，本文提出首个利用单纯形复形结构进行时空建模的方法——Modern Structure-Aware Simplicial Spatiotemporal Neural Network (ModernSASST)。该方法在高维单纯形上实施时空随机游走，并融合可并行化的时序卷积网络，以高效捕捉高阶拓扑结构。实验表明，该方法在保持计算效率的同时，显著提升了对复杂时空模式的建模能力。源代码已公开于GitHub。
原文摘要 · Abstract (English)
Spatiotemporal modeling has evolved beyond simple time series analysis to become fundamental in structural time series analysis. While current research extensively employs graph neural networks (GNNs) for spatial feature extraction with notable success, these networks are limited to capturing only pairwise relationships, despite real-world networks containing richer topological relationships. Additionally, GNN-based models face computational challenges that scale with graph complexity, limiting their applicability to large networks. To address these limitations, we present Modern Structure-Aware Simplicial SpatioTemporal neural network (ModernSASST), the first approach to leverage simplicial complex structures for spatiotemporal modeling. Our method employs spatiotemporal random walks on high-dimensional simplicial complexes and integrates parallelizable Temporal Convolutional Networks to capture high-order topological structures while maintaining computational efficiency. Our source code is publicly available on GitHub\footnote{Code is available at: https://github.com/ComplexNetTSP/ST_RUM.
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。