Adaptive Spatial-Temporal Graph Convolution Networks for Collaborative Local-Global Learning in Traffic Prediction
- 16 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 72 (10) , 12653-12663
Abstract
The rapid growth of vehicles as countries become more developed has brought great challenges to traffic prediction. Recent works model only local or global spatial-temporal features via graph neural networks (GNNs). Furthermore, the explicit graph structure information may contain bias, in particular, the lack of connections among multiple nodes when in fact, they are interdependent. This results in the inability to accommodate information interaction and the underutilization of high-quality information. In this paper, we design an adaptive spatial-temporal graph convolution networks (ASTGCNs) to collaboratively learn local-global spatial-temporal information for traffic prediction. Specifically, we obtain different local spatial-temporal information (i.e. spatial-temporal information of each temporal point) by dividing the global spatial-temporal information along the temporal dimension. For local spatial-temporal information, we establish an adaptive graph convolution to enhance the ability of graph convolution networks (GCNs) in managing bias in the explicit graph structure. We then employ an attention mechanism to learn the local summarization of dynamic node neighborhoods to obtain high-quality information. For global spatial-temporal information, a temporal convolution network (TCN) block and the ordinary differential equation (ODE) are utilized in our model. In essence, our proposed ASTGCNs integrates adaptive graph convolution, attention mechanism, TCN block and ODE to collaboratively learn local-global spatial-temporal information. Experimental results show that our ASTGCNs is superior to state-of-art (SOTA) methods when applied to four real-world datasets.Keywords
Funding Information
- Key Program of the National Natural Science Foundation of China (61133005, 61432005)
- China Scholarship Council (202106130053)
- Postgraduate Scientific Research Innovation Project of Hunan Province (CX20220413)
This publication has 33 references indexed in Scilit:
- TAGCN: Station-level demand prediction for bike-sharing system via a temporal attention graph convolution networkInformation Sciences, 2021
- MS-Net: Multi-Source Spatio-Temporal Network for Traffic Flow PredictionIEEE Transactions on Intelligent Transportation Systems, 2021
- ST-LBAGAN: Spatio-temporal learnable bidirectional attention generative adversarial networks for missing traffic data imputationKnowledge-Based Systems, 2021
- Online Traffic Flow Prediction for Edge Computing-Enhanced Autonomous and Connected VehiclesIEEE Transactions on Vehicular Technology, 2021
- FTPG: A Fine-Grained Traffic Prediction Method With Graph Attention Network Using Big Trace DataIEEE Transactions on Intelligent Transportation Systems, 2021
- Multiple local 3D CNNs for region-based prediction in smart citiesInformation Sciences, 2021
- DSANet2019
- A periodicity-based parallel time series prediction algorithm in cloud computing environmentsInformation Sciences, 2019
- Roadside Traffic Sign Detection Based on Faster R-CNN2019
- Real-time road traffic prediction with spatio-temporal correlationsTransportation Research Part C: Emerging Technologies, 2011