统一建模交通流时空依赖，提升预测精度与效率
Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting
- 用低秩矩阵统一存储时空及关联信息，动态更新
- 在多个真实数据集上实现更高精度，计算开销小
- 模块化设计，可融合多种图神经网络，适合交通预测研究
交通流的时空预测面临空间与时间因素复杂交互的挑战。现有方法常孤立处理时空维度，忽略其关键耦合关系。本文提出时空统一模型（STUM），通过分布对齐与特征融合，统一建模空间与时间依赖，并缓解时空异质性。核心是自适应时空单元细胞（ASTUC），利用低秩矩阵无缝存储、更新和交互空间、时间及其相关性。模型模块化，可集成骨干网络、特征提取器、残差融合块和预测模块，协同提升预测效果。在多个真实数据集上的实验表明，STUM持续提升预测性能，且计算成本极低。超参数优化、预训练分析与结果可视化进一步验证了有效性。代码已公开：https://anonymous.4open.science/r/STUM-E4F0。
原文摘要 · Abstract (English)
Predicting spatio-temporal traffic flow presents significant challenges due to complex interactions between spatial and temporal factors. Existing approaches often address these dimensions in isolation, neglecting their critical interdependencies. In this paper, we introduce the Spatio-Temporal Unitized Model (STUM), a unified framework designed to capture both spatial and temporal dependencies while addressing spatio-temporal heterogeneity through techniques such as distribution alignment and feature fusion. It also ensures both predictive accuracy and computational efficiency. Central to STUM is the Adaptive Spatio-temporal Unitized Cell (ASTUC), which utilizes low-rank matrices to seamlessly store, update, and interact with space, time, as well as their correlations. Our framework is also modular, allowing it to integrate with various spatio-temporal graph neural networks through components such as backbone models, feature extractors, residual fusion blocks, and predictive modules to collectively enhance forecasting outcomes. Experimental results across multiple real-world datasets demonstrate that STUM consistently improves prediction performance with minimal computational cost. These findings are further supported by hyperparameter optimization, pre-training analysis, and result visualization. We provide our source code for reproducibility at https://anonymous.4open.science/r/STUM-E4F0.
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。