An official source code for paper GraphLearner:Graph Node Clustering with Fully Learnable Augmentation, accepted by ACM MM 24. Any communications or issues are welcomed. Please contact [email protected]. If you find this repository useful to your research or work, it is really appreciate to star this repository. ❤️

Illustration of GraphLearner:Graph Node Clustering with Fully Learnable Augmentation.

The proposed GraphLearner is implemented with python 3.8.8 on a NVIDIA 3090 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

python train.py 

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

@inproceedings{GraphLearner,
  title={Graphlearner: Graph node clustering with fully learnable augmentation},
  author={Yang, Xihong and Min, Erxue and Liang, Ke and Liu, Yue and Wang, Siwei and Zhou, Sihang and Wu, Huijun and Liu, Xinwang and Zhu, En},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  pages={5517--5526},
  year={2024}
}