This work EGRC-Net has been accepted by IEEE Transactions on Image Processing.

DOI: https://ieeexplore.ieee.org/abstract/document/10326461

URL: https://arxiv.org/abs/2211.10627

We have added comments in the code, and the specific details can correspond to the explanation in the paper. Please get in touch with me (zhihapeng3-c@my.cityu.edu.hk) if you have any issues.

We appreciate it if you use this code and cite our related papers, which can be cited as follows,

@article{peng2023egrc,
title={EGRC-Net: Embedding-Induced Graph Refinement Clustering Network},
author={Peng, Zhihao and Liu, Hui and Jia, Yuheng and Hou, Junhui},
journal={IEEE Transactions on Image Processing},
volume={32},
pages={6457--6468},
year={2023},
publisher={IEEE} }

@article{peng2022deep,
title={Deep Attention-guided Graph Clustering with Dual Self-supervision},
author={Peng, Zhihao and Liu, Hui and Jia, Yuheng and Hou, Junhui},
journal={IEEE Transactions on Circuits and Systems for Video Technology},
year={2022},
publisher={IEEE} }

@inproceedings{peng2021attention,
title={Attention-driven graph clustering network},
author={Peng, Zhihao and Liu, Hui and Jia, Yuheng and Hou, Junhui},
booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
pages={935--943},
year={2021} }

Environment

• Python[3.7.9]
• Pytorch[1.7.1]
• GPU (GeForce RTX 2080 Ti) & (NVIDIA GeForce RTX 3090) & (Quadro RTX 8000)

Hyperparameters

To run code

• Step 1: set the hyperparameters for the specific dataset;
• Step 2: python EGRC-Net.py

• For example, if u would like to run AGCN on the DBLP dataset, u need to first set {0.01, 0.1, 0.1} for DBLP; then run the command "python main_DBLP.py"

• To obtain the pre-trained weights of AE, you can modify the provided primary model to keep the AE module solely. For your convenience, I have followed the above process and given a pretrain.py code that pre-trains AE for another dataset.

Data

Due to the limitation of GitHub, we share the data in [here].