INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging(WWW-23)

This repository is Tensorflow implementation for the WWW-23 paper INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging.

The in-depth interpretation of this paper is here in Chinese.

Data

• The METR-LA dataset is available at Google Drive or Baidu Yun, provided by DCRNN, and should be put into the corresponding data/ folder.
• The Beijing dataset can be found in this repository under the /Beijing/data/ path
• The Xiamen dataset is still being compiled and will be coming soon

Results

Citation

@article{DBLP:journals/corr/abs-2302-02738,
  author = {Chuanpan Zheng and Xiaoliang Fan and Cheng Wang and Jianzhong Qi and Chaochao Chen and Longbiao Chen},
  title = {{INCREASE:} Inductive Graph Representation Learning for Spatio-Temporal Kriging},
  journal = {CoRR},
  volume = {abs/2302.02738},
  year = {2023},
  url = {https://doi.org/10.48550/arXiv.2302.02738},
  doi = {10.48550/arXiv.2302.02738},
  eprinttype = {arXiv},
  eprint = {2302.02738}
  }