Current Visitors:

PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction

J. Jiang, C. Han, WX. Zhao, and J. Wang

in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'23)

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 effec- tively model the complex spatial-temporal dependencies in traffic data. Spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising meth- ods 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 traf- fic 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 intro- duced to highlight spatial dependencies from short- and long- range views. Moreover, a traffic delay-aware feature transfor- mation module is proposed to empower PDFormer with the capability of explicitly modeling the time delay of spatial in- formation 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.

PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction
PDFormer_ Propagation Delay-Aware Dynami
Adobe Acrobat Document 5.7 MB

The code for this paper is released in GitHub


title={PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction},

author={Jiawei Jiang and Chengkai Han and Wayne Xin Zhao and Jingyuan Wang},

booktitle = {{AAAI}},

publisher = {{AAAI} Press},

year = {2023}