ADGC: Awesome Deep Graph Clustering

ADGC is a collection of state-of-the-art (SOTA), novel deep graph clustering methods (papers, codes and datasets). Any other interesting papers and codes are welcome. Any problems, please contact [email protected]. If you find this repository useful to your research or work, it is really appreciated to star this repository. :sparkles: If you use our code or the processed datasets in this repository for your research, please cite 2-3 papers in the citation part here. :heart:

What is Deep Graph Clustering?

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. More details can be found in the survey paper. Link

 ![](./assets/logo_new.png) 

Important Survey Papers

Papers

LLM-based Deep Graph Clustering

New-architecture Deep Graph Clustering

Temporal Deep Graph Clustering

Deep Graph Clustering with Unknown Cluster Number

Reconstructive Deep Graph Clustering

Adversarial Deep Graph Clustering

Contrastive Deep Graph Clustering

Multi-View and Multimodal Deep Graph Clustering

Attributed Hypergraph Clustering

Federated Deep Graph Clustering

Applications

Other Related Papers

Deep Clustering

Deep Hierarchical Clustering

Other Related Methods

Benchmark Datasets

We divide the datasets into two categories, i.e. graph datasets and non-graph datasets. Graph datasets are some graphs in real-world, such as citation networks, social networks and so on. Non-graph datasets are NOT graph type. However, if necessary, we could construct "adjacency matrices" by K-Nearest Neighbors (KNN) algorithm.

Quick Start

• Step1: Download all datasets from [Google Drive | Nutstore]. Optionally, download some of them from URLs in the tables (Google Drive)
• Step2: Unzip them to ./dataset/
• Step3: Change the type and the name of the dataset in main.py
• Step4: Run the main.py

Code

• utils.py
  1. load_graph_data: load graph datasets
  2. load_data: load non-graph datasets
  3. normalize_adj: normalize the adjacency matrix
  4. diffusion_adj: calculate the graph diffusion
  5. construct_graph: construct the knn graph for non-graph datasets
  6. numpy_to_torch: convert numpy to torch
  7. torch_to_numpy: convert torch to numpy
• clustering.py
  1. setup_seed: fix the random seed
  2. evaluation: evaluate the performance of clustering
  3. k_means: K-means algorithm
• visualization.py
  1. t_sne: t-SNE algorithm
  2. similarity_plot: visualize cosine similarity matrix of the embedding or feature

Datasets Details

About the introduction of each dataset, please check here

1. Graph Datasets

Edges: Here, we just count the number of undirected edges.

2. Non-graph Datasets

Citation

@article{AGCSurvey,
  title={Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering},
  author={Yunhui Liu and Yue Liu and Yongchao Liu and Tao Zheng and Stan Z. Li and Xinwang Liu and Tieke He},
  year={2026},
  eprint={2603.20829},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}

@inproceedings{PyAGC,
  title={Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering},
  author={Yunhui Liu and Pengyu Qiu and Yu Xing and Yongchao Liu and Peng Du and Chuntao Hong and Jiajun Zheng and Tao Zheng and Tieke He},
  booktitle={The Fortieth Annual Conference on Neural Information Processing Systems Evaluations and Datasets Track},
  year={2026},
  url={https://openreview.net/forum?id=qBpyipVo0p}
}

@inproceedings{ITR,
  title={Identify Then Recommend: Towards Unsupervised Group Recommendation},
  author={Liu, Yue and Zhu, Shihao and Yang, Tianyuan and Ma, Jian and Zhong, Wenliang},
  booktitle={Proc. of NeurIPS},
  year={2024}
}

@article{ELCRec,
  title={End-to-end Learnable Clustering for Intent Learning in Recommendation},
  author={Liu, Yue and Zhu, Shihao and Xia, Jun and Ma, Yingwei and Ma, Jian and Zhong, Wenliang and Zhang, Guannan and Zhang, Kejun and Liu, Xinwang},
  booktitle={Proceedings of International Conference on Neural Information Processing Systems},
  year={2024}
}

@article{deep_graph_clustering_survey,
  title={A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application},
  author={Liu, Yue and Xia, Jun and Zhou, Sihang and Wang, Siwei and Guo, Xifeng and Yang, Xihong and Liang, Ke and Tu, Wenxuan and Li, Z. Stan and Liu, Xinwang},
  journal={arXiv preprint arXiv:2211.12875},
  year={2022}
}

@article{SCGC,
  title={Simple contrastive graph clustering},
  author={Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang and Wang, Siwei and Liang, Ke and Tu, Wenxuan and Li, Liang},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2023},
  publisher={IEEE}
}

@inproceedings{Dink_Net,
  title={Dink-net: Neural clustering on large graphs},
  author={Liu, Yue and Liang, Ke and Xia, Jun and Zhou, Sihang and Yang, Xihong and Liu, Xinwang and Li, Stan Z},
  booktitle={Proceedings of International Conference on Machine Learning},
  year={2023}
}

@inproceedings{TGC_ML_ICLR,
  title={Deep Temporal Graph Clustering},
  author={Liu, Meng and Liu, Yue and Liang, Ke and Tu, Wenxuan and Wang, Siwei and Zhou, Sihang and Liu, Xinwang},
  booktitle={The 12th International Conference on Learning Representations},
  year={2024}
}

@inproceedings{HSAN,
  title={Hard sample aware network for contrastive deep graph clustering},
  author={Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang and Wang, Zhen and Liang, Ke and Tu, Wenxuan and Li, Liang and Duan, Jingcan and Chen, Cancan},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={37},
  number={7},
  pages={8914-8922},
  year={2023}
}

@inproceedings{DCRN,
  title={Deep Graph Clustering via Dual Correlation Reduction},
  author={Liu, Yue and Tu, Wenxuan and Zhou, Sihang and Liu, Xinwang and Song, Linxuan and Yang, Xihong and Zhu, En},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={36},
  number={7},
  pages={7603-7611},
  year={2022}
}

@inproceedings{liuyue_RGC,
  title={Reinforcement Graph Clustering with Unknown Cluster Number},
  author={Liu, Yue and Liang, Ke and Xia, Jun and Yang, Xihong and Zhou, Sihang and Liu, Meng and Liu, Xinwang and Li, Stan Z},
  booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
  pages={3528--3537},
  year={2023}
}

@article{RGAE,
  title={Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering},
  author={Mrabah, Nairouz and Bouguessa, Mohamed and Touati, Mohamed Fawzi and Ksantini, Riadh},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  year={2022}
}

@article{yu2025guard,
  title   = {G${}^2$uardFL: Safeguarding Federated Learning against Backdoor Attacks via Attributed Client Graph Clustering},
  author  = {Hao Yu and Chuan Ma and Meng Liu and Tianyu Du and Ming Ding and Tao Xiang and Shouling Ji and Xinwang Liu},
  journal = {IEEE Transactions on Information Forensics and Security},
  year    = {2025},
  doi     = {10.1109/TIFS.2025.3639985}
}

Other Related Awesome Repository

PyAGC

PyDGC

Awesome-Deep-Group-Recommendation

Awesome-Partial-Graph-Machine-Learning

Awesome-Knowledge-Graph-Reasoning

Awesome-Temporal-Graph-Learning

Awesome-Deep-Multiview-Clustering