Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction
This work addresses traffic prediction for urban management, offering an incremental improvement by reducing computational costs while maintaining accuracy.
The authors tackled traffic speed prediction by proposing a factorized Spatial-Temporal Tensor Graph Convolutional Network that integrates spatial and temporal information into a graph and uses tensor decomposition to reduce computational burden and suppress noise. Their method achieved state-of-the-art performance on two real-world datasets.
Accurate traffic prediction is crucial to the guidance and management of urban traffics. However, most of the existing traffic prediction models do not consider the computational burden and memory space when they capture spatial-temporal dependence among traffic data. In this work, we propose a factorized Spatial-Temporal Tensor Graph Convolutional Network to deal with traffic speed prediction. Traffic networks are modeled and unified into a graph that integrates spatial and temporal information simultaneously. We further extend graph convolution into tensor space and propose a tensor graph convolution network to extract more discriminating features from spatial-temporal graph data. To reduce the computational burden, we take Tucker tensor decomposition and derive factorized a tensor convolution, which performs separate filtering in small-scale space, time, and feature modes. Besides, we can benefit from noise suppression of traffic data when discarding those trivial components in the process of tensor decomposition. Extensive experiments on two real-world traffic speed datasets demonstrate our method is more effective than those traditional traffic prediction methods, and meantime achieves state-of-the-art performance.