Crowd Flow Forecasting with Multi-Graph Neural Networks

Crowd flow forecasting is of great significance for urban traffic management and personal travel planning. Due to the complexity of the urban geographic structure and the highly nonlinear temporal and spatial dependence on crowd flow, accurate forecasting becomes very challenging. Recent research works usually divided cities into regions of the same size and coded as heat-maps, for cities with complex terrain, heat-maps contain many invalid data, which have a negative effect on the acquisition of spatial dependence. In order to decrease the effect, we encode the crowd flow into graphs and propose a multi-graph neural network based model to solve the crowd flow forecasting problem. We first construct two K-NN graphs by the Euclidean distance and the Pearson correlation coefficient respectively and the spatial dependence is captured through the spatial block composed of Graph Attention Networks(GAT) and ChebNet, then another ChebNet is deployed to fuse the spatial dependency of the two graphs. Afterward, we adapted a LSTM to capture the temporal dependence of all regions separately and use self-attention mechanism and fully connected layer to (a) the receptive filed of CNN’s filget prediction results. Extensive experiment results based on two real-world datasets demonstrate that our model achieves an important performance on other baselines.

[1]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[2]  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.

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

[4]  Tianbao Yang,et al.  Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data , 2018, KDD.

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

[6]  Xianfeng Tang,et al.  Modeling Spatial-Temporal Dynamics for Traffic Prediction , 2018, ArXiv.

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

[8]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[9]  I Okutani,et al.  Dynamic prediction of traffic volume through Kalman Filtering , 1984 .

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

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

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

[13]  Henry X. Liu,et al.  Use of Local Linear Regression Model for Short-Term Traffic Forecasting , 2003 .

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

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

[16]  Tianrui Li,et al.  Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks , 2017, Artif. Intell..

[17]  Steven I-Jy Chien,et al.  Development of a Hybrid Model for Dynamic Travel-Time Prediction , 2003 .

[18]  Yunbo Wang,et al.  Eidetic 3D LSTM: A Model for Video Prediction and Beyond , 2019, ICLR.

[19]  D. T. Lee,et al.  Travel-time prediction with support vector regression , 2004, IEEE Transactions on Intelligent Transportation Systems.

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

[21]  Weimin Zheng,et al.  StepDeep: A Novel Spatial-temporal Mobility Event Prediction Framework based on Deep Neural Network , 2018, KDD.