/a-Decoupling-Framework-for-Graph-Neural-Networks

code for paper ” A Block-Based Adaptive Decoupling Framework for Graph Neural Networks“

Primary LanguagePython

A Block-Based Adaptive Decoupling Framework for Graph Neural Networks

code for paper ”A Block-Based Adaptive Decoupling Framework for Graph Neural Networks“(https://doi.org/10.3390/e24091190)

Dependencies

  • python == 3.8
  • pytorch == 1.9.0
  • dgl == 0.7.2
  • network == 2.5
  • scipy == 1.6.1

Usage

  • train.py is used for semi-supervised node classification and full_supervised.py is used for fully supervised node classification.

Citation

@article{shen2022block,
title={A Block-Based Adaptive Decoupling Framework for Graph Neural Networks},
author={Shen, Xu and Zhang, Yuyang and Xie, Yu and Wong, Ka-Chun and Peng, Chengbin},
journal={Entropy},
volume={24},
number={9},
pages={1190},
year={2022},
publisher={Multidisciplinary Digital Publishing Institute}
}