Cluster-guided Contrastive Graph Clustering Network

An official source code for paper Cluster-guided Contrastive Graph Clustering Network , accepted by AAAI 2023. 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

We propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms.

Figure 1: Overall framework of CCGC.

Requirements

The proposed CCGC is implemented with python 3.7 on a NVIDIA 2080Ti GPU.

Python package information is summarized in requirements.txt:

• torch==1.7.1
• tqdm==4.59.0
• numpy==1.19.2
• munkres==1.1.4
• scikit_learn==1.2.0

Quick Start

python train.py

Clustering Results

Table 1: Clustering results of our proposed CCGC and twelve baselines on six datasets.

Figure 2: 2D t-SNE visualization of six methods on two datasets.

Citation

If you find this project useful for your research, please cite your paper with the following BibTeX entry.

@inproceedings{CCGC,
  title={Cluster-guided Contrastive Graph Clustering Network},
  author={Yang, Xihong and Liu, Yue and Zhou, Sihang and Wang, Siwei and Tu, Wenxuan and Zheng, Qun and Liu, Xinwang and Fang, Liming and Zhu, En},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={37},
  number={9},
  pages={10834--10842},
  year={2023}
}