PDFormer: 面向交通流预测的传播延迟感知动态长距离Transformer
PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
AI总结:
针对现有交通流预测GNN模型静态建模、难捕捉长程依赖及忽略传播延迟的问题,提出PDFormer模型,通过动态空间自注意力、长短程图掩码及延迟感知模块实现精准预测,在6个数据集上达SOTA且效率可观、可解释性强。
摘要:
作为智能交通系统的核心技术,交通流预测具有广泛的应用场景。交通流预测的根本挑战在于如何有效建模交通数据中复杂的时空依赖关系。时空图神经网络(GNN)模型已成为解决该问题最具潜力的方法之一。然而,基于GNN的模型在交通预测中存在三大局限:其一,大多数方法以静态方式建模空间依赖,限制了对动态城市交通模式的学习能力;其二,大多数方法仅考虑短程空间信息,无法捕捉长程空间依赖;其三,这些方法忽略了交通系统中不同地点之间交通状况的传播存在时间延迟这一事实。为此,我们提出了一种新型的传播延迟感知动态长距离Transformer,即PDFormer,用于实现精准的交通流预测。具体而言,我们设计了空间自注意力模块以捕捉动态空间依赖;随后引入两种图掩码矩阵,从短程和长程视角突出空间依赖关系;此外,提出了交通延迟感知特征变换模块,使PDFormer具备显式建模空间信息传播时间延迟的能力。在六个真实世界公开交通数据集上的大量实验结果表明,我们的方法不仅能达到最优(state-of-the-art)性能,还展现出具有竞争力的计算效率。此外,我们对学习到的时空注意力图进行了可视化,使模型具备高度可解释性。
英文摘要:
As a core technology of Intelligent Transportation System, traffic flow prediction has a wide range of applications. The fundamental challenge in traffic flow prediction is to effectively model the complex spatial-temporal dependencies in traffic data. Spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. However, GNN-based models have three major limitations for traffic prediction: i) Most methods model spatial dependencies in a static manner, which limits the ability to learn dynamic urban traffic patterns; ii) Most methods only consider short-range spatial information and are unable to capture long-range spatial dependencies; iii) These methods ignore the fact that the propagation of traffic conditions between locations has a time delay in traffic systems. To this end, we propose a novel Propagation Delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Specifically, we design a spatial self-attention module to capture the dynamic spatial dependencies. Then, two graph masking matrices are introduced to highlight spatial dependencies from short- and long-range views. Moreover, a traffic delay-aware feature transformation module is proposed to empower PDFormer with the capability of explicitly modeling the time delay of spatial information propagation. Extensive experimental results on six real-world public traffic datasets show that our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency. Moreover, we visualize the learned spatial-temporal attention map to make our model highly interpretable.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。