Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting

Accurate traffic state prediction is the foundation of transportation control and guidance. It is very challenging due to the complex spatiotemporal dependencies in traffic data. Existing works cannot perform well for multi-step traffic prediction that involves long future time period. The spatiotemporal information dilution becomes serve when the time gap between input step and predicted step is large, especially when traffic data is not sufficient or noisy. To address this issue, we propose a multi-spatial graph convolution based Seq2Seq model. Our main novelties are three aspects: (1) We enrich the spatiotemporal information of model inputs by fusing multi-view features (time, location and traffic states) (2) We build multiple kinds of spatial correlations based on both prior knowledge and data-driven knowledge to improve model performance especially in insufficient or noisy data cases. (3) A spatiotemporal attention mechanism based on reachability knowledge is novelly designed to produce high-level features fed into decoder of Seq2Seq directly to ease information dilution. Our model is evaluated on two real world traffic datasets and achieves better performance than other competitors.

[1]  Jing Li,et al.  Graph CNNs for Urban Traffic Passenger Flows Prediction , 2018, 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

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

[3]  Wei Cao,et al.  When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks , 2018, AAAI.

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

[5]  Hong Cheng,et al.  Predicting Path Failure In Time-Evolving Graphs , 2019, KDD.

[6]  Juanjuan Zhao,et al.  Multi-STGCnet: A Graph Convolution Based Spatial-Temporal Framework for Subway Passenger Flow Forecasting , 2020, 2020 International Joint Conference on Neural Networks (IJCNN).

[7]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[8]  Tao Shen,et al.  DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding , 2017, AAAI.

[9]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[10]  Kenli Li,et al.  Gated Residual Recurrent Graph Neural Networks for Traffic Prediction , 2019, AAAI.

[11]  Ke Zhang,et al.  Optimized Graph Convolution Recurrent Neural Network for Traffic Prediction , 2021, IEEE Transactions on Intelligent Transportation Systems.

[12]  Qi Zhang,et al.  GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction , 2019, IJCAI.

[13]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

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

[15]  Wei Cao,et al.  Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting , 2019, AAAI.

[16]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

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

[18]  Huadong Ma,et al.  A vehicle classification system based on hierarchical multi-SVMs in crowded traffic scenes , 2016, Neurocomputing.

[19]  Zhifeng Bao,et al.  Crowdsourcing-based real-time urban traffic speed estimation: From trends to speeds , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

[20]  Yu Zheng,et al.  Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks , 2019, IEEE Transactions on Knowledge and Data Engineering.

[21]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[22]  Zhirui Ye,et al.  Short‐Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition , 2007, Comput. Aided Civ. Infrastructure Eng..

[23]  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.

[24]  Yinhai Wang,et al.  Multistep speed prediction on traffic networks: A deep learning approach considering spatio-temporal dependencies , 2019, Transportation Research Part C: Emerging Technologies.

[25]  Linpeng Huang,et al.  Revisiting Flow Information for Traffic Prediction , 2019, ArXiv.

[26]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[27]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[28]  Zhanxing Zhu,et al.  3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting , 2019, ArXiv.

[29]  Jia Liu,et al.  Urban flows prediction from spatial-temporal data using machine learning: A survey , 2019, ArXiv.

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

[31]  Jieping Ye,et al.  Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting , 2019, AAAI.

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

[33]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[34]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[35]  Simon Scheider,et al.  A Vector-Geometry Based Spatial kNN-Algorithm for Traffic Frequency Predictions , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[36]  Hao Ma,et al.  GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs , 2018, UAI.

[37]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[38]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[39]  Christian S. Jensen,et al.  Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

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

[41]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[42]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[43]  James J. Q. Yu,et al.  Real-Time Traffic Speed Estimation With Graph Convolutional Generative Autoencoder , 2019, IEEE Transactions on Intelligent Transportation Systems.

[44]  Changshui Zhang,et al.  Switching ARIMA model based forecasting for traffic flow , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[45]  Jiannong Cao,et al.  GCGAN: Generative Adversarial Nets with Graph CNN for Network-Scale Traffic Prediction , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[46]  Lina Yao,et al.  STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting , 2019, IJCAI.

[47]  Kejiang Ye,et al.  How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey , 2020, ArXiv.

[48]  Hang Li,et al.  Temporal Graph Convolutional Networks for Traffic Speed Prediction Considering External Factors , 2019, 2019 20th IEEE International Conference on Mobile Data Management (MDM).

[49]  Haitham Al-Deek,et al.  Predictions of Freeway Traffic Speeds and Volumes Using Vector Autoregressive Models , 2009, J. Intell. Transp. Syst..

[50]  Zhanxing Zhu,et al.  ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling , 2019, ArXiv.

[51]  Dafang Zhang,et al.  Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting , 2019, AAAI.

[52]  Qi Zhang,et al.  Kernel-Weighted Graph Convolutional Network: A Deep Learning Approach for Traffic Forecasting , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[53]  Minlie Huang,et al.  GAKE: Graph Aware Knowledge Embedding , 2016, COLING.

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