Heterophilous distribution propagation for Graph Neural Networks (HDP)

This is the code for Heterophilous distribution propagation for Graph Neural Networks (HDP).

Main Requirements

• python >= 3.6.13
• numpy >= 1.19.2
• pytorch >= 1.10.2
• dgl-cuda >= 0.8.1
• torch-geometric >= 2.0.3

How to Run

python main.py  --dataset={dataset}

Citation

If you find this repo useful for your research, please consider citing our paper:

@article{ZHENG2025107014,
    author = {Zhuonan Zheng and Sheng Zhou and Hongjia Xu and Ming Gu and Yilun Xu and Ao Li and Yuhong Li and Jingjun Gu and Jiajun Bu},
    doi = {https://doi.org/10.1016/j.neunet.2024.107014},
    issn = {0893-6080},
    journal = {Neural Networks},
    keywords = {Graph Neural Networks, Graph representation learning, Graph heterophily},
    pages = {107014},
    title = {Heterophilous distribution propagation for Graph Neural Networks},
    url = {https://www.sciencedirect.com/science/article/pii/S0893608024009432},
    volume = {184},
    year = {2025},
    Bdsk-Url-1 = {https://www.sciencedirect.com/science/article/pii/S0893608024009432},
    Bdsk-Url-2 = {https://doi.org/10.1016/j.neunet.2024.107014}

}