/GMAN

GMAN: A Graph Multi-Attention Network for Traffic Prediction (GMAN, https://fanxlxmu.github.io/publication/aaai2020/) was accepted by AAAI-2020.

Primary LanguagePythonApache License 2.0Apache-2.0

GMAN: A Graph Multi-Attention Network for Traffic Prediction (AAAI-2020)

This is the implementation of Graph Multi-Attention Network in the following paper:
Chuanpan Zheng, Xiaoliang Fan*, Cheng Wang, and Jianzhong Qi. "GMAN: A Graph Multi-Attention Network for Traffic Prediction", Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 2020, 34(01): 1234-1241.

Data

The datasets are available at Google Drive or Baidu Yun, provided by DCRNN, and should be put into the corresponding data/ folder.

Requirements

Python 3.7.10, tensorflow 1.14.0, numpy 1.16.4, pandas 0.24.2

Results

Third-party re-implementations

A Pytorch implementaion by VincLee8188 is available at GMAN-Pytorch.

Citation

If you find this repository useful in your research, please cite the following paper:

@inproceedings{ GMAN-AAAI2020,
  author     = "Chuanpan Zheng and Xiaoliang Fan and Cheng Wang and Jianzhong Qi"
  title      = "GMAN: A Graph Multi-Attention Network for Traffic Prediction",
  booktitle  = "AAAI",
  pages      = "1234--1241",
  year       = "2020"
}