面向交通流预测的结构引导时空注意力图神经网络

中文摘要 AI 辅助

结合图卷积与注意力机制的深度时空模型因具备捕捉复杂时空依赖的出色能力，在网络级交通流预测中展现出优异性能。尽管这类模型预测效果良好，但其部署在安全关键型城市系统中仍受限于固有的透明度不足问题。现有事后诊断方法常受虚假相关性困扰，无法揭示支配交通动态的内在决策机制，导致可解释性欠佳、运行可信度有限。为应对这些挑战，本文提出结构引导时空注意力图神经网络（SGSAN）。与依赖无约束自适应图的传统架构不同，SGSAN明确学习静态有向依赖图（DDG）以识别交通状态的不变宏观传播路径。我们进一步引入基于InfoNCE的软耦合机制，将模型的动态时空注意力锚定到该结构先验，通过使基于注意力的推理与已识别的宏观依赖对齐、防止过度依赖短暂局部噪声，在确保预测稳健性的同时，为模型的决策过程提供机理解释。此外，开发了一种解耦的两阶段优化框架，以解决结构发现与预测误差最小化之间的根本冲突。在多个真实世界数据集上开展的大量实验表明，SGSAN实现了最先进的预测精度，同时提供与交通网络物理逻辑有机契合的内置可解释性。

英文摘要

Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often struggle with spurious correlations and fail to unveil the intrinsic decision-making mechanisms governing traffic dynamics, resulting in suboptimal interpretability and limited operational trustworthiness. To address these challenges, this paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN). Departing from traditional architectures that rely on unconstrained adaptive graphs, SGSAN explicitly learns a static Directed Dependency Graph (DDG) to identify the invariant macroscopic propagation paths of traffic states. We further introduce an InfoNCE-based soft-coupling mechanism that anchors the model's dynamic spatiotemporal attention to this structural prior, offering a mechanistic account of the model's decision-making process while ensuring robust forecasting by aligning attention-based reasoning with identified macroscopic dependencies and preventing over-reliance on ephemeral local noise. Furthermore, a decoupled two-stage optimization framework is developed to resolve the fundamental conflict between structural discovery and predictive error minimization. Extensive experiments on multiple real-world datasets demonstrate that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with the physical logic of traffic networks.

发表机构

• University of California, Berkeley（加利福尼亚大学伯克利分校）
• Tongji University（同济大学）

机构由 AI 辅助整理，请以论文原文为准。