D IFFUSION C ONVOLUTIONAL R ECURRENT N EURAL N ETWORK : D ATA -D RIVEN T RAFFIC F ORECASTING

Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (3) inherent difficulty of long-term forecasting. To address these challenges, we propose to model the traffic flow as a diffusion process on a directed graph and introduce Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow. Specifically, DCRNN captures the spatial dependency using bidirectional random walks on the graph, and the temporal dependency using the encoder-decoder architecture with scheduled sampling. We evaluate the framework on two real-world large scale road network traffic datasets and observe consistent improvement of 12% - 15% over state-of-the-art baselines.

[1]  Wei Xu,et al.  DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting , 2017, 2018 International Joint Conference on Neural Networks (IJCNN).

[2]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[3]  Yotam Hechtlinger,et al.  A Generalization of Convolutional Neural Networks to Graph-Structured Data , 2017, ArXiv.

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

[5]  Xavier Bresson,et al.  Structured Sequence Modeling with Graph Convolutional Recurrent Networks , 2016, ICONIP.

[6]  Inderjit S. Dhillon,et al.  Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction , 2016, NIPS.

[7]  Huachun Tan,et al.  Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework , 2016, ArXiv.

[8]  Gaetano Fusco,et al.  Short-term speed predictions exploiting big data on large urban road networks , 2016 .

[9]  Xiuwen Yi,et al.  DNN-based prediction model for spatio-temporal data , 2016, SIGSPATIAL/GIS.

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

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

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

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

[14]  Shang-Hua Teng,et al.  Scalable Algorithms for Data and Network Analysis , 2016, Found. Trends Theor. Comput. Sci..

[15]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[16]  Ugur Demiryurek,et al.  Latent Space Model for Road Networks to Predict Time-Varying Traffic , 2016, KDD.

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

[18]  Yu Cheng,et al.  Efficient Sampling for Gaussian Graphical Models via Spectral Sparsification , 2015, COLT.

[19]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

[20]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

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

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

[23]  Jignesh M. Patel,et al.  Big data and its technical challenges , 2014, CACM.

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

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

[26]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[27]  Yoshua Bengio,et al.  Algorithms for Hyper-Parameter Optimization , 2011, NIPS.

[28]  Xing Xie,et al.  Discovering spatio-temporal causal interactions in traffic data streams , 2011, KDD.

[29]  Ying Sun,et al.  Gaussian Processes for Short-Term Traffic Volume Forecasting , 2010 .

[30]  Ennio Cascetta,et al.  Transportation Systems Engineering: Theory and Methods , 2001 .

[31]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[32]  Bin Yu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017 .

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

[34]  J. Yosinski,et al.  Time-series Extreme Event Forecasting with Neural Networks at Uber , 2017 .

[35]  Yunpeng Wang,et al.  A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting , 2016 .

[36]  Donald Richard Drew,et al.  Traffic flow theory and control , 1968 .

[37]  P. Frasconi,et al.  This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 1 Short-Term Traffic Flow Forecasting: An Experimental , 2022 .