T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction

12 Nov 2018  ·  Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li ·

Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence. To capture the spatial and temporal dependence simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is in combination with the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures to capture spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data to capture temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://github.com/lehaifeng/T-GCN.

PDF Abstract

Datasets


Introduced in the Paper:

SZ-Taxi

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Traffic Prediction SZ-Taxi GRU MAE @ 15min 2.6814 # 4
MAE @ 30min 2.7009 # 3
MAE @ 45min 2.7207 # 3
MAE @ 60min 2.7431 # 4
Traffic Prediction SZ-Taxi T-GCN MAE @ 15min 2.7061 # 5
MAE @ 30min 2.7452 # 5
MAE @ 45min 2.7666 # 5
MAE @ 60min 2.7889 # 5

Methods