How to select a suitable spatial weighting scheme for convolutional graph neural networks (ConvGNNs) is challenging. In this study, we propose a ConvGNN, termed learnable graph convolutional (LGC) network, which learns spatial weightings between a road and its k-hop neighbours as learnable parameters in the spatial convolutional operator. A dynamic LGC (DLGC) network is further proposed to learn the dynamics of spatial weightings by explicitly considering the temporal correlations of spatial weightings at different times of the day. A multi-temporal DLGC (MTDLGC) network is developed for forecasting traffic variables in road networks. Results of case study suggest that the MT-DLGC network can achieve higher prediction accuracy than other state-of-the-art baselines. Both LGC and DLGC networks can be used as general spatial weighting schemes for baselines with better forecasting performance than existing spatial weighting schemes, e.g., graph attention. The source code of this study is available publicly at https://github.com/Mayaohong/MTDLGC.
Graph convolutional networks with learnable spatial weightings for traffic forecasting applications
TRANSPORTMETRICA A: TRANSPORT SCIENCE
B. Y. CHEN ET AL.
2025-01-02
30 pages
Article (Journal)
Electronic Resource
English
Spatial‐temporal correlation graph convolutional networks for traffic forecasting
DOAJ | 2023
|Spatial‐temporal correlation graph convolutional networks for traffic forecasting
Wiley | 2023
|IEEE | 1974
|Dynamic Spatial–Temporal Convolutional Networks for Traffic Flow Forecasting
Transportation Research Record | 2023
|