/MGCN

[TKDD 2024] An official source code for paper Mixed Graph Contrastive Network for Semi-Supervised Node Classification.

Primary LanguagePythonMIT LicenseMIT

Mixed Graph Contrastive Network for Semi-Supervised Node Classification

GitHub stars GitHub forks visitors

An official source code for paper Mixed Graph Contrastive Network for Semi-Supervised Node Classification. Any communications or issues are welcomed. Please contact xihong_edu@163.com. If you find this repository useful to your research or work, it is really appreciate to star this repository. ❤️


Overview

Illustration of Mixed Graph Contrastive Network for Semi-Supervised Node Classification (MGCN) mechanism.

Requirements

The proposed MGCN is implemented with python 3.8.8 on a NVIDIA 1080 Ti GPU.

Python package information is summarized in requirements.txt:

  • torch==1.8.0
  • tqdm==4.61.2
  • numpy==1.21.0
  • tensorboard==2.8.0

Quick Start

python train.py 

Citation

If you use code or datasets in this repository for your research, please cite our paper.

@article{MGCN,
  title={Mixed Graph Contrastive Network for Semi-Supervised Node Classification},
  author={Yang, Xihong and Liu, Yue and Zhou, Sihang and Liu, Xinwang and Zhu, En},
  journal={arXiv preprint arXiv:2206.02796},
  year={2022}
}