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. ❤️

---

What's 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.

​

Important Survey Papers

Papers

1. K-Means: "Algorithm AS 136: A k-means clustering algorithm" [paper|code]
2. SAE (AAAI14): "Learning Deep Representations for Graph Clustering" [paper|code]
3. DEC (ICML16): "Unsupervised Deep Embedding for Clustering Analysis" [paper|code]
4. GAE/VGAE (NeurIPS16): "Variational Graph Auto-Encoders" [paper|code]
5. DCN (ICML17): "Towards k-means-friendly spaces: Simultaneous deep learning and clustering" [paper|code]
6. IDEC (IJCAI17): "Improved Deep Embedded Clustering with Local Structure Preservation" [paper|code]
7. MGAE (CIKM17): "MGAE: Marginalized Graph Autoencoder for Graph Clustering" [paper|code]
8. NetVAE (IJCAI19): "Network-Specific Variational Auto-Encoder for Embedding in Attribute Networks" [paper]
9. DAEGC (IJCAI19): "Attributed Graph Clustering: A Deep Attentional Embedding Approach" [paper|code]
10. AGAE (IJCAI19): "Adversarial Graph Embedding for Ensemble Clustering" [paper]
11. AGC (IJCAI19): "Attributed Graph Clustering via Adaptive Graph Convolution" [paper|code]
12. GALA (ICCV19): "Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning" [paper|code]
13. ARGA/ARVGA (TCYB19): "Learning Graph Embedding with Adversarial Training Methods" [paper|code]
14. MCGC (TIP19): "Multiview Consensus Graph Clustering" [paper|code]
15. RWR-GAE (arXiv19): "RWR-GAE: Random Walk Regularization for Graph Auto Encoders" [paper|code]
16. HAN (WWW2019): "Heterogeneous Graph Attention Network" [paper|code]
17. DAG (ICCKE20): "Attributed Graph Clustering via Deep Adaptive Graph Maximization" [paper]
18. SDCN/SDCN_Q (WWW20): "Structural Deep Clustering Network" [paper|code]
19. AGE (SIGKDD20): "Adaptive Graph Encoder for Attributed Graph Embedding" [paper|code]
20. MAGCN (IJCAI20): "Multi-View Attribute Graph Convolution Networks for Clustering" [paper|code]
21. MVGRL (ICML20): "Contrastive Multi-View Representation Learning on Graphs" [paper|code]
22. Cross-Graph (ICDM20): "Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure" [paper|code]
23. CGCN/GMM-VGAE (AAAI20): "Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning" [paper|code]
24. DMGI (AAAI20): "Unsupervised Attributed Multiplex Network Embedding" [paper|code]
25. O2MAC (WWW20): "One2Multi Graph Autoencoder for Multi-view Graph Clustering" [paper|code]
26. MAGNN (WWW20): "MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding" [paper|code]
27. MinCutPool (ICML20): "Spectral Clustering with Graph Neural Networks for Graph Pooling" [paper|code]
28. GCAGC (CVPR20): "Adaptive Graph Convolutional Network with Attention Graph Clustering for Co saliency Detection" [paper|code]
29. DBGAN (CVPR20): "Distribution-induced Bidirectional GAN for Graph Representation Learning" [paper|code]
30. DGVAE (NeurIPS20): "Dirichlet Graph Variational Autoencoder" [paper|code]
31. CAGNN (arXiv20): "Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning" [paper]
32. GDCL (IJCAI21): "Graph Debiased Contrastive Learning with Joint Representation Clustering" [paper|code]
33. GCC (ICCV21): "Graph Contrastive Clustering" [paper|code]
34. MCGC (NeurIPS21): "Multi-view Contrastive Graph Clustering" [paper|code]
35. COLES (NeurIPS21): "Contrastive Laplacian Eigenmaps" [paper|code]
36. AGCN (MM2021): "Attention-driven Graph Clustering Network" [paper|code]
37. DFCN (AAAI21): "Deep Fusion Clustering Network" [paper|code]
38. SCAGC (arXiv21): "Self-supervised Contrastive Attributed Graph Clustering" [paper]
39. R-GAE (arXiv21): "Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering" [paper|code]
40. WARGA (arXiv21): "Wasserstein Adversarially Regularized Graph Autoencoder" [paper|code]
41. DAGC (arXiv21, extension of AGCN): ”Deep Attention-guided Graph Clustering with Dual Self-supervision“ [paper|code]
42. MGCCN (arXiv21): "Multilayer Graph Contrastive Clustering Network" [paper]
43. Graph-MVP (arXiv21): "Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs" [paper|code]
44. MvAGC (IJCAI21): "Graph Filter-based Multi-view Attributed Graph Clustering" [paper|code]
45. GIC (PAKDD21): "Graph InfoClust: Maximizing Coarse-Grain Mutual Information in Graphs" [paper|code]
46. HDMI (WWW21): "High-order Deep Multiplex Infomax" [paper|code]
47. SOLI (Neurocomputing21): "Deep node clustering based on mutual information maximization" [paper|code]
48. MAGC (TKDE21): "Multi-view Attributed Graph Clustering" [paper|code]
49. AHGAE (TKDE21): "Adaptive Hypergraph Auto-Encoder for Relational Data Clustering" [paper]
50. AdaGAE (TPAMI21): "Adaptive Graph Auto-Encoder for General Data Clustering" [paper|code]
51. NAS-GC (TCYB21): "Smoothness Sensor: Adaptive Smoothness Transition Graph Convolutions for Attributed Graph Clustering" [paper|code]
52. SENet (NN21): "Spectral embedding network for attributed graph clustering" [paper]
53. GC-VGE (PR22): "Graph Clustering via Variational Graph Embedding" [paper]
54. DNENC (PR22): "Deep neighbor-aware embedding for node clustering in attributed graphs" [paper]
55. SDSNE(AAAI22): "Stationary diffusion state neural estimation for multiview clustering" [paper|code]
56. SAIL(AAAI22): "SAIL: Self-Augmented Graph Contrastive Learning" [paper]
57. AFGRL (AAAI22): "Augmentation-Free Self-Supervised Learning on Graphs" [paper|code]
58. DCRN (AAAI22): "Deep Graph Clustering via Dual Correlation Reduction" [paper|code]
59. AUTOSSL (ICLR22): "Automated Self-Supervised Learning For Graphs" [paper|code]
60. SAGES (TKDE22): "SAGES: Scalable Attributed Graph Embedding with Sampling for Unsupervised Learning" [paper]
61. GCC (WSDM22): "Efficient Graph Convolution for Joint Node Representation Learning and Clustering" [paper|code]
62. IDCRN (arXiv22, extension of DCRN): "Improved Dual Correlation Reduction Network" [paper]
63. MVGC (NN22) : "Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation" [paper|code]

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

   Dataset	Samples	Dimension	Edges	Classes	URL
   CORA	2708	1433	5278	7	cora.zip
   CITESEER	3327	3703	4552	6	citeseer.zip
   PUBMED	19717	500	44324	3	pubmed.zip
   DBLP	4057	334	3528	4	dblp.zip
   CITE	3327	3703	4552	6	cite.zip
   ACM	3025	1870	13128	3	acm.zip
   AMAP	7650	745	119081	8	amap.zip
   AMAC	13752	767	245861	10	amac.zip
   CORAFULL	19793	8710	63421	70	corafull.zip
   WIKI	2405	4973	8261	19	wiki.zip
   COCS	18333	6805	81894	15	cocs.zip
   BAT	131	81	1038	4	bat.zip
   EAT	399	203	5994	4	eat.zip
   UAT	1190	239	13599	4	uat.zip

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

2. Non-graph Datasets

   Dataset	Samples	Dimension	Type	Classes	URL
   USPS	9298	256	Image	10	usps.zip
   HHAR	10299	561	Record	6	hhar.zip
   REUT	10000	2000	Text	4	reut.zip

Citation

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

@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={AAAI Conference on Artificial Intelligence},
  year={2022}
}
@article{mrabah2021rethinking,
  title={Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering},
  author={Mrabah, Nairouz and Bouguessa, Mohamed and Touati, Mohamed Fawzi and Ksantini, Riadh},
  journal={arXiv preprint arXiv:2107.08562},
  year={2021}
}

Other Related Awesome Repository

awesome-awesome-machine-learning

Awesome Incomplete Graph Representation Learning

awesome-self-supervised-gnn