Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.

[1]  Juanjuan Zhao,et al.  How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey , 2020, IEEE Transactions on Intelligent Transportation Systems.

[2]  Chenliang Li,et al.  A Deep Neural Framework for Sales Forecasting in E-Commerce , 2019, CIKM.

[3]  Suhang Wang,et al.  Unsupervised Representation Learning of Spatial Data via Multimodal Embedding , 2019, CIKM.

[4]  Yunkai Zhang,et al.  You May Not Need Order in Time Series Forecasting , 2019, ArXiv.

[5]  Xianfeng Tang,et al.  Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values , 2019, AAAI.

[6]  Matthias W. Seeger,et al.  Deep State Space Models for Time Series Forecasting , 2018, NeurIPS.

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

[8]  Guokun Lai,et al.  Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks , 2017, SIGIR.

[9]  Hsiang-Fu Yu,et al.  Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting , 2019, NeurIPS.

[10]  Weiyao Lin,et al.  Spatial-Temporal Transformer Networks for Traffic Flow Forecasting , 2020, ArXiv.

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

[12]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

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

[14]  Jieping Ye,et al.  Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction , 2018, AAAI.

[15]  Naren Ramakrishnan,et al.  EpiDeep: Exploiting Embeddings for Epidemic Forecasting , 2019, KDD.

[16]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[17]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

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

[19]  Wei Liu,et al.  Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network , 2020, CIKM.

[20]  Yong Yu,et al.  Matrix Factorization for Spatio-Temporal Neural Networks with Applications to Urban Flow Prediction , 2019, CIKM.

[21]  Ying Zhang,et al.  Multivariate Time Series Imputation with Generative Adversarial Networks , 2018, NeurIPS.

[22]  Ao Tang,et al.  DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting , 2019, CIKM.

[23]  Wei Cao,et al.  BRITS: Bidirectional Recurrent Imputation for Time Series , 2018, NeurIPS.

[24]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

[25]  Youfang Lin,et al.  Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting , 2020, AAAI.

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

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

[28]  Robert P. Dick,et al.  Multi-Group Encoder-Decoder Networks to Fuse Heterogeneous Data for Next-Day Air Quality Prediction , 2019, IJCAI.

[29]  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.

[30]  Lina Yao,et al.  Passenger Demand Forecasting with Multi-Task Convolutional Recurrent Neural Networks , 2019, PAKDD.

[31]  Jiahui Wang,et al.  Vector Autoregressive Models for Multivariate Time Series , 2003 .

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

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

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

[35]  Lina Yao,et al.  Spatio-Temporal Graph Convolutional and Recurrent Networks for Citywide Passenger Demand Prediction , 2019, CIKM.

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

[37]  Junbo Zhang,et al.  Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning , 2019, KDD.

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

[39]  Valentin Flunkert,et al.  DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks , 2017, International Journal of Forecasting.

[40]  Yanming Shen,et al.  A Comprehensive Survey on Traffic Prediction , 2020, ArXiv.

[41]  Pravin Varaiya,et al.  Freeway Performance Measurement System: Mining Loop Detector Data , 2001 .

[42]  Minh N. Do,et al.  STREETS: A Novel Camera Network Dataset for Traffic Flow , 2019, NeurIPS.

[43]  Sander Bohte,et al.  Conditional Time Series Forecasting with Convolutional Neural Networks , 2017, 1703.04691.

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

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

[46]  Dacheng Tao,et al.  Multi-task Recurrent Neural Networks and Higher-order Markov Random Fields for Stock Price Movement Prediction: Multi-task RNN and Higer-order MRFs for Stock Price Classification , 2019, KDD.