DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting

Shiyong Lan, Yitong Ma, Weikang Huang, Wenwu Wang, Hongyu Yang, Pyang Li
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:11906-11917, 2022.

Abstract

As a typical problem in time series analysis, traffic flow prediction is one of the most important application fields of machine learning. However, achieving highly accurate traffic flow prediction is a challenging task, due to the presence of complex dynamic spatial-temporal dependencies within a road network. This paper proposes a novel Dynamic Spatial-Temporal Aware Graph Neural Network (DSTAGNN) to model the complex spatial-temporal interaction in road network. First, considering the fact that historical data carries intrinsic dynamic information about the spatial structure of road networks, we propose a new dynamic spatial-temporal aware graph based on a data-driven strategy to replace the pre-defined static graph usually used in traditional graph convolution. Second, we design a novel graph neural network architecture, which can not only represent dynamic spatial relevance among nodes with an improved multi-head attention mechanism, but also acquire the wide range of dynamic temporal dependency from multi-receptive field features via multi-scale gated convolution. Extensive experiments on real-world data sets demonstrate that our proposed method significantly outperforms the state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-lan22a, title = {{DSTAGNN}: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting}, author = {Lan, Shiyong and Ma, Yitong and Huang, Weikang and Wang, Wenwu and Yang, Hongyu and Li, Pyang}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {11906--11917}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/lan22a/lan22a.pdf}, url = {https://proceedings.mlr.press/v162/lan22a.html}, abstract = {As a typical problem in time series analysis, traffic flow prediction is one of the most important application fields of machine learning. However, achieving highly accurate traffic flow prediction is a challenging task, due to the presence of complex dynamic spatial-temporal dependencies within a road network. This paper proposes a novel Dynamic Spatial-Temporal Aware Graph Neural Network (DSTAGNN) to model the complex spatial-temporal interaction in road network. First, considering the fact that historical data carries intrinsic dynamic information about the spatial structure of road networks, we propose a new dynamic spatial-temporal aware graph based on a data-driven strategy to replace the pre-defined static graph usually used in traditional graph convolution. Second, we design a novel graph neural network architecture, which can not only represent dynamic spatial relevance among nodes with an improved multi-head attention mechanism, but also acquire the wide range of dynamic temporal dependency from multi-receptive field features via multi-scale gated convolution. Extensive experiments on real-world data sets demonstrate that our proposed method significantly outperforms the state-of-the-art methods.} }
Endnote
%0 Conference Paper %T DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting %A Shiyong Lan %A Yitong Ma %A Weikang Huang %A Wenwu Wang %A Hongyu Yang %A Pyang Li %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-lan22a %I PMLR %P 11906--11917 %U https://proceedings.mlr.press/v162/lan22a.html %V 162 %X As a typical problem in time series analysis, traffic flow prediction is one of the most important application fields of machine learning. However, achieving highly accurate traffic flow prediction is a challenging task, due to the presence of complex dynamic spatial-temporal dependencies within a road network. This paper proposes a novel Dynamic Spatial-Temporal Aware Graph Neural Network (DSTAGNN) to model the complex spatial-temporal interaction in road network. First, considering the fact that historical data carries intrinsic dynamic information about the spatial structure of road networks, we propose a new dynamic spatial-temporal aware graph based on a data-driven strategy to replace the pre-defined static graph usually used in traditional graph convolution. Second, we design a novel graph neural network architecture, which can not only represent dynamic spatial relevance among nodes with an improved multi-head attention mechanism, but also acquire the wide range of dynamic temporal dependency from multi-receptive field features via multi-scale gated convolution. Extensive experiments on real-world data sets demonstrate that our proposed method significantly outperforms the state-of-the-art methods.
APA
Lan, S., Ma, Y., Huang, W., Wang, W., Yang, H. & Li, P.. (2022). DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:11906-11917 Available from https://proceedings.mlr.press/v162/lan22a.html.

Related Material