Traffic forecasting is a particularly challenging application of
spatiotemporal forecasting, due to the time-varying traffic patterns and the
complicated spatial dependencies on road networks. To address this challenge,
we learn the traffic network as a graph and propose a novel deep learning
framework, Traffic Graph Convolutional Long Short-Term Memory Neural Network
(TGC-LSTM), to learn the interactions between roadways in the traffic network
and forecast the network-wide traffic state. We define the traffic graph
convolution based on the physical network topology. The relationship between
the proposed traffic graph convolution and the spectral graph convolution is
also discussed. An L1-norm on graph convolution weights and an L2-norm on graph
convolution features are added to the model's loss function to enhance the
interpretability of the proposed model. Experimental results show that the
proposed model outperforms baseline methods on two real-world traffic state
datasets. The visualization of the graph convolution weights indicates that the
proposed framework can recognize the most influential road segments in
real-world traffic networks.
%0 Generic
%1 cui2018traffic
%A Cui, Zhiyong
%A Henrickson, Kristian
%A Ke, Ruimin
%A Pu, Ziyuan
%A Wang, Yinhai
%D 2018
%K graph_neural_networks traffic_prediction
%T Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning
Framework for Network-Scale Traffic Learning and Forecasting
%U http://arxiv.org/abs/1802.07007
%X Traffic forecasting is a particularly challenging application of
spatiotemporal forecasting, due to the time-varying traffic patterns and the
complicated spatial dependencies on road networks. To address this challenge,
we learn the traffic network as a graph and propose a novel deep learning
framework, Traffic Graph Convolutional Long Short-Term Memory Neural Network
(TGC-LSTM), to learn the interactions between roadways in the traffic network
and forecast the network-wide traffic state. We define the traffic graph
convolution based on the physical network topology. The relationship between
the proposed traffic graph convolution and the spectral graph convolution is
also discussed. An L1-norm on graph convolution weights and an L2-norm on graph
convolution features are added to the model's loss function to enhance the
interpretability of the proposed model. Experimental results show that the
proposed model outperforms baseline methods on two real-world traffic state
datasets. The visualization of the graph convolution weights indicates that the
proposed framework can recognize the most influential road segments in
real-world traffic networks.
@misc{cui2018traffic,
abstract = {Traffic forecasting is a particularly challenging application of
spatiotemporal forecasting, due to the time-varying traffic patterns and the
complicated spatial dependencies on road networks. To address this challenge,
we learn the traffic network as a graph and propose a novel deep learning
framework, Traffic Graph Convolutional Long Short-Term Memory Neural Network
(TGC-LSTM), to learn the interactions between roadways in the traffic network
and forecast the network-wide traffic state. We define the traffic graph
convolution based on the physical network topology. The relationship between
the proposed traffic graph convolution and the spectral graph convolution is
also discussed. An L1-norm on graph convolution weights and an L2-norm on graph
convolution features are added to the model's loss function to enhance the
interpretability of the proposed model. Experimental results show that the
proposed model outperforms baseline methods on two real-world traffic state
datasets. The visualization of the graph convolution weights indicates that the
proposed framework can recognize the most influential road segments in
real-world traffic networks.},
added-at = {2021-10-13T23:23:54.000+0200},
author = {Cui, Zhiyong and Henrickson, Kristian and Ke, Ruimin and Pu, Ziyuan and Wang, Yinhai},
biburl = {https://www.bibsonomy.org/bibtex/2659abd247d8a91d54ca98391914238eb/peter.ralph},
interhash = {9d10b4e1e4e7346daeb059297a63ccdf},
intrahash = {659abd247d8a91d54ca98391914238eb},
keywords = {graph_neural_networks traffic_prediction},
note = {cite arxiv:1802.07007},
timestamp = {2021-10-13T23:23:54.000+0200},
title = {Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning
Framework for Network-Scale Traffic Learning and Forecasting},
url = {http://arxiv.org/abs/1802.07007},
year = 2018
}