/HGNN-AC

Source code of "WWW21 - Heterogeneous Graph Neural Network via Attribute Completion"

Primary LanguagePython

Heterogeneous Graph Neural Network via Attribute Completion

This repository contains the demo code of the paper:

Heterogeneous Graph Neural Network via Attribute Completion

which has been accepted by WWW2021.

Dependencies

  • Python3
  • NumPy
  • SciPy
  • scikit-learn
  • NetworkX
  • DGL
  • PyTorch

Datasets

The preprocessed datasets are available at Baidu Netdisk(password: hgnn) or Google Drive.

Please extract the zip file to folder data.

Example

  • python run_DBLP.py
  • python run_IMDB.py
  • python run_ACM.py

Please refer to the code for detailed parameters.

Acknowledgements

The demo code is implemented based on MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding.

Citing

@inproceedings{hgnn-ac,
 title={Heterogeneous Graph Neural Network via Attribute Completion},
 author={Di Jin and Cuiying Huo and Chundong Liang and Liang Yang},
 booktitle = {WWW},
 year={2021}
}