The official code of WWW2021 paper: Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework

• Python version >= 3.6
• PyTorch version >= 1.7.1
• DGL
• Optuna (optional)

1. use python train_dgl.py --dataset=XXX --teacher=XXX to run teacher model.
2. use python spawn_worker.py --dataset=XXX --teacher=XXX to run student model, we provide our hyper-parameters setting as reported in our paper, and an AutoML version for hyper-parameters search. (Our code supports Optuna to search best hyper-parameters for knowledge distillation. You can use --automl to run Optuna code.)

You can add your own datasets to folder data, the formats should accord to DGL requirements.

You can add your own teacher or student model by adding them into folder models, and following the format of model run.

There are some results on GCN teacher model, with different datasets and student varients. More results can be seen in our paper.

Please cite our paper if you use this code in your own work:

@inproceedings{yang2021extract,
  title={Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework},
  author={Cheng Yang and Jiawei Liu and Chuan Shi},
  booktitle={Proceedings of The Web Conference 2021 (WWW ’21)},
  publisher={ACM},
  year={2021}
}

Please open an issue or contact [email protected] with any questions.