Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues

Traffic forecasting plays an important role of modern Intelligent Transportation Systems (ITS). With the recent rapid advancement in deep learning, graph neural networks (GNNs) have become an emerging research issue for improving the traffic forecasting problem. Specifically, one of the main types of GNNs is the spatial-temporal GNN (ST-GNN), which has been applied to various time-series forecasting applications. This study aims to provide an overview of recent ST-GNN models for traffic forecasting. Particularly, we propose a new taxonomy of ST-GNN by dividing existing models into four approaches such as graph convolutional recurrent neural network, fully graph convolutional network, graph multi-attention network, and self-learning graph structure. Sequentially, we present experimental results based on the reconstruction of representative models using selected benchmark datasets to evaluate the main contributions of the key components in each type of ST-GNN. Finally, we discuss several open research issues for further investigations.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[3]  Hung-yi Lee,et al.  Temporal pattern attention for multivariate time series forecasting , 2018, Machine Learning.

[4]  Zhongcheng Wu,et al.  Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction , 2020, IEEE Access.

[5]  Yonghua Zhou,et al.  Parallel computing method of deep belief networks and its application to traffic flow prediction , 2019, Knowl. Based Syst..

[6]  Prasanna Balaprakash,et al.  Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting , 2019, Transportation Research Record: Journal of the Transportation Research Board.

[7]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[8]  Yongqi Sun,et al.  An effective dynamic spatiotemporal framework with external features information for traffic prediction , 2020, Applied Intelligence.

[9]  Baocai Yin,et al.  Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions , 2021, IEEE Transactions on Intelligent Transportation Systems.

[10]  Jai E. Jung,et al.  Game theoretic approach on Real‐time decision making for IoT‐based traffic light control , 2017, Concurr. Comput. Pract. Exp..

[11]  Xianfeng Tang,et al.  Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction , 2018, AAAI.

[12]  Jaegul Choo,et al.  ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed , 2020, CIKM.

[13]  Cheng Wang,et al.  GMAN: A Graph Multi-Attention Network for Traffic Prediction , 2019, AAAI.

[14]  Si Zhang,et al.  Graph convolutional networks: a comprehensive review , 2019, Computational Social Networks.

[15]  Weinan Zhang,et al.  Spatio-Temporal Meta Learning for Urban Traffic Prediction , 2020, IEEE Transactions on Knowledge and Data Engineering.

[16]  Yann Dauphin,et al.  Pay Less Attention with Lightweight and Dynamic Convolutions , 2019, ICLR.

[17]  Xiaojun Chang,et al.  Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks , 2020, KDD.

[18]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[19]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[20]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[21]  Ning Feng,et al.  Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting , 2019, AAAI.

[22]  Khac-Hoai Nam Bui,et al.  An Automated Hyperparameter Search-Based Deep Learning Model for Highway Traffic Prediction , 2021, IEEE Transactions on Intelligent Transportation Systems.

[23]  James J. Q. Yu,et al.  Spatial-Temporal Graph Attention Networks: A Deep Learning Approach for Traffic Forecasting , 2019, IEEE Access.

[24]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[25]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[26]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[27]  Ghazaleh Khodabandelou,et al.  Link traffic speed forecasting using convolutional attention-based gated recurrent unit , 2020, Applied Intelligence.

[28]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Donald F. Towsley,et al.  Diffusion-Convolutional Neural Networks , 2015, NIPS.

[30]  Khac-Hoai Nam Bui,et al.  UVDS: A New Dataset for Traffic Forecasting with Spatial-Temporal Correlation , 2021, ACIIDS.

[31]  Khac-Hoai Nam Bui,et al.  Traffic Density Classification Using Sound Datasets: An Empirical Study on Traffic Flow at Asymmetric Roads , 2020, IEEE Access.

[32]  Jing Jiang,et al.  Graph WaveNet for Deep Spatial-Temporal Graph Modeling , 2019, IJCAI.

[33]  Richard Socher,et al.  Pointer Sentinel Mixture Models , 2016, ICLR.

[34]  Aniekan Essien,et al.  A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders , 2020, IEEE Transactions on Industrial Informatics.

[35]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[36]  Yinhai Wang,et al.  Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting , 2018, IEEE Transactions on Intelligent Transportation Systems.

[37]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[38]  Qi Zhang,et al.  Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting , 2020, NeurIPS.

[39]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.