Home

Awesome

Coupled layer-wise convolutional network for transportation demand prediction

Thanks for your interests! The data is available in: https://pan.baidu.com/s/1usoSQtzUk8JDh-v0B7f52g with the password kyt9. Put the taxi_data.h5 and bike_data.h5 in data/nogrid.

Although the adjacency matrix generated by distance is not used in our method, we put it in the data/adj_data.zip.

Citation

If you find this repository, e.g., the code and the datasets, useful in your research, please cite the following paper:

@inproceedings{ye2021coupled,
    title={Coupled Layer-wise Graph Convolution for Transportation Demand Prediction},
    author={Ye, Junchen and Sun, Leilei and Du, Bowen and Fu, Yanjie and Xiong, Hui},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    volume={35},
    number={5},
    pages={4617--4625},
    year={2021}
}