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. ✨ If you use our code or the processed datasets in this repository for your research, please cite 1-2 papers in the citation part here.
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. More details can be found in the survey paper. Link
Important Survey Papers
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2023 | An Overview of Advanced Deep Graph Node Clustering | TCSS | Link | - |
| 2022 | A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application | arXiv | Link | Link |
| 2022 | A Comprehensive Survey on Community Detection with Deep Learning | TNNLS | Link | - |
| 2020 | A Comprehensive Survey on Graph Neural Networks | TNNLS | Link | - |
| 2020 | Deep Learning for Community Detection: Progress, Challenges and Opportunities | IJCAI | Link | - |
| 2018 | A survey of clustering with deep learning: From the perspective of network architecture | IEEE Access | Link | - |
Papers
Reconstructive Deep Graph Clustering
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2023 | Graph Clustering Network with Structure Embedding Enhanced (GC-SEE) | PR | link | link |
| 2023 | Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering (DGCN) | ICML | Link | Link |
| 2023 | Deep Temporal Graph Clustering (TGC) | arXiv | Link | - |
| 2022 | Escaping Feature Twist: A Variational Graph Auto-Encoder for Node Clustering (FT-VGAE) | IJCAI | Link | Link |
| 2022 | Deep Attention-guided Graph Clustering with Dual Self-supervision (DAGC) | TCSVT | Link | Link |
| 2022 | Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering (R-GAE) | TKDE | Link | Link |
| 2022 | Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution (GEC-CSD) | NN | Link | - |
| 2022 | Exploring temporal community structure via network embedding (VGRGMM) | TCYB | Link | - |
| 2022 | Cluster-Aware Heterogeneous Information Network Embedding (VaCA-HINE) | WSDM | Link | - |
| 2022 | Efficient Graph Convolution for Joint Node Representation Learning and Clustering (GCC) | WSDM | Link | Link |
| 2022 | ZINB-based Graph Embedding Autoencoder for Single-cell RNA-seq Interpretations (scTAG) | AAAI | Link | Link |
| 2022 | Graph community infomax(GCI) | TKDD | Link | - |
| 2022 | Deep graph clustering with multi-level subspace fusion (DGCSF) | PR | Link | - |
| 2022 | Graph Clustering via Variational Graph Embedding (GC-VAE) | PR | Link | - |
| 2022 | Deep neighbor-aware embedding for node clustering in attributed graphs (DNENC) | PR | Link | - |
| 2022 | Collaborative Decision-Reinforced Self-Supervision for Attributed Graph Clustering (CDRS) | TNNLS | Link | Link |
| 2022 | Embedding Graph Auto-Encoder for Graph Clustering (EGAE) | TNNLS | Link | Link |
| 2021 | Self-Supervised Graph Convolutional Network for Multi-View Clustering (SGCMC) | TMM | Link | Link |
| 2021 | Adaptive Hypergraph Auto-Encoder for Relational Data Clustering (AHGAE) | TKDE | Link | - |
| 2021 | Attention-driven Graph Clustering Network (AGCN) | ACM MM | Link | Link |
| 2021 | Deep Fusion Clustering Network (DFCN) | AAAI | Link | Link |
| 2020 | Graph Clustering with Graph Neural Networks (DMoN) | arXiv | Link | Link |
| 2020 | Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning (CGCN) | AAAI | Link | Link |
| 2020 | Deep multi-graph clustering via attentive cross-graph association (DMGC) | WSDM | Link | Link |
| 2020 | Going Deep: Graph Convolutional Ladder-Shape Networks (GCLN) | AAAI | Link | - |
| 2020 | Multi-view attribute graph convolution networks for clustering (MAGCN) | IJCAI | Link | Link |
| 2020 | One2Multi Graph Autoencoder for Multi-view Graph Clustering (O2MAC) | WWW | Link | Link |
| 2020 | Structural Deep Clustering Network (SDCN/SDCN_Q) | WWW | Link | Link |
| 2020 | Dirichlet Graph Variational Autoencoder (DGVAE) | NeurIPS | Link | Link |
| 2019 | RWR-GAE: Random Walk Regularization for Graph Auto Encoders (RWR-GAE) | arXiv | Link | Link |
| 2019 | Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning (GALA) | ICCV | Link | Link |
| 2019 | Attributed Graph Clustering: A Deep Attentional Embedding Approach (DAEGC) | IJCAI | Link | Link |
| 2019 | Network-Specific Variational Auto-Encoder for Embedding in Attribute Networks (NetVAE) | IJCAI | Link | - |
| 2017 | Graph Clustering with Dynamic Embedding (GRACE) | arXiv | Link | Link |
| 2017 | MGAE: Marginalized Graph Autoencoder for Graph Clustering (MGAE) | CIKM | Link | Link |
| 2017 | Learning Community Embedding with Community Detection and Node Embedding on Graphs (ComE) | CIKM | Link | Link |
| 2016 | Deep Neural Networks for Learning Graph Representations (DNGR) | AAAI | Link | Link |
| 2015 | Heterogeneous Network Embedding via Deep Architectures (HNE) | SIGKDD | Link | - |
| 2014 | Learning Deep Representations for Graph Clustering (GraphEncoder) | AAAI | Link | Link |
Adversarial Deep Graph Clustering
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2021 | Wasserstein Adversarially Regularized Graph Autoencoder | arXiv | Link | Link |
| 2020 | JANE: Jointly adversarial network embedding (JANE) | IJCAI | Link | - |
| 2019 | Adversarial Graph Embedding for Ensemble Clustering (AGAE) | IJCAI | Link | - |
| 2019 | CommunityGAN: Community Detection with Generative Adversarial Nets (CommunityGAN) | WWW | Link | Link |
| 2019 | ProGAN: Network embedding via proximity generative adversarial network (ProGAN) | SIGKDD | Link | - |
| 2019 | Learning Graph Embedding with Adversarial Training Methods (ARGA/ARVGA) | TCYB | Link | Link |
| 2019 | Adversarially Regularized Graph Autoencoder for Graph Embedding (ARGA/ARVGA) | IJCAI | Link | Link |
| 2022 | Unsupervised network embedding beyond homophily (SELENE) | TMLR | Link | Link |
Contrastive Deep Graph Clustering
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2023 | Dink-Net: Neural Clustering on Large Graphs | ICML | Link | Link |
| 2023 | CONGREGATE: Contrastive Graph Clustering in Curvature Spaces | IJCAI | Link | Link |
| 2023 | Simple Contrastive Graph Clustering (SCGC) | TNNLS | Link | - |
| 2023 | Hard Sample Aware Network for Contrastive Deep Graph Clustering (HSAN) | AAAI | Link | Link |
| 2023 | Cluster-guided Contrastive Graph Clustering Network (CCGC) | AAAI | Link | Link |
| 2023 | Contrastive Graph Clustering in Curvature Spaces | arXiv | Link | - |
| 2022 | NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering (NCAGC) | arXiv | Link | Link |
| 2022 | SCGC : Self-Supervised Contrastive Graph Clustering (SCGC) | arXiv | Link | Link |
| 2022 | Improved Dual Correlation Reduction Network (IDCRN) | arXiv | Link | - |
| 2022 | S3GC: Scalable Self-Supervised Graph Clustering (S3GC) | NeurIPS | Link | Link |
| 2022 | Self-consistent Contrastive Attributed Graph Clustering with Pseudo-label Prompt (SCAGC) | TMM | Link | Link |
| 2022 | CGC: Contrastive Graph Clustering for Community Detection and Tracking (CGC) | WWW | Link | - |
| 2022 | Towards Unsupervised Deep Graph Structure Learning (SUBLIME) | WWW | Link | Link |
| 2022 | Attributed Graph Clustering with Dual Redundancy Reduction (AGC-DRR) | IJCAI | Link | Link |
| 2022 | Deep Graph Clustering via Dual Correlation Reduction (DCRN) | AAAI | Link | Link |
| 2022 | RepBin: Constraint-Based Graph Representation Learning for Metagenomic Binning (RepBin) | AAAI | Link | Link |
| 2022 | Augmentation-Free Self-Supervised Learning on Graphs (AFGRL) | AAAI | Link | Link |
| 2022 | SAIL: Self-Augmented Graph Contrastive Learning (SAIL) | AAAI | Link | - |
| 2021 | Graph Debiased Contrastive Learning with Joint Representation Clustering (GDCL) | IJCAI | Link | Link |
| 2021 | Multi-view Contrastive Graph Clustering (MCGC) | NeurIPS | Link | Link |
| 2021 | Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning (HeCo) | SIGKDD | Link | Link |
| 2020 | Adaptive Graph Encoder for Attributed Graph Embedding (AGE) | SIGKDD | Link | Link |
| 2020 | CommDGI: Community Detection Oriented Deep Graph Infomax (CommDGI) | CIKM | Link | Link |
| 2020 | Contrastive Multi-View Representation Learning on Graphs (MVGRL) | ICML | Link | Link |
Other Related Papers
Deep Clustering
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2023 | Beyond The Evidence Lower Bound: Dual Variational Graph Auto-Encoders For Node Clustering | SDM | Link | Link |
| 2023 | GC-Flow: A Graph-Based Flow Network for Effective Clustering | ICLM | Link | Link |
| 2023 | Scalable Attributed-Graph Subspace Clustering (SAGSC) | AAAI | Link | Link |
| 2022 | Adaptive Attribute and Structure Subspace Clustering Network (AASSC-Net) | TIP | Link | Link |
| 2022 | Twin Contrastive Learning for Online Clustering | IJCV | Link | Link |
| 2022 | Non-Graph Data Clustering via O(n) Bipartite Graph Convolution | TPAMI | Link | Link |
| 2022 | Ada-nets: Face clustering via adaptive neighbor discovery in the structure space | ICLR | Link | Link |
| 2021 | Adaptive Graph Auto-Encoder for General Data Clustering | TPAMI | Link | Link |
| 2021 | Contrastive Clustering | AAAI | Link | Link |
| 2017 | Towards k-means-friendly spaces: Simultaneous deep learning and clustering (DCN) | ICML | Link | Link |
| 2017 | Improved Deep Embedded Clustering with Local Structure Preservation (IDEC) | IJCAI | Link | Link |
| 2016 | Unsupervised Deep Embedding for Clustering Analysis (DEC) | ICML | Link | Link |
Other Related Methods
| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2022 | Deep linear graph attention model for attributed graph clustering | Knowl Based Syst | Link | - |
| 2022 | Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning | WWW | Link | - |
| 2022 | X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning (X-GOAL) | arXiv | Link | - |
| 2022 | Deep Graph Clustering with Multi-Level Subspace Fusion | PR | Link | - |
| 2022 | GRACE: A General Graph Convolution Framework for Attributed Graph Clustering | TKDD | Link | Link |
| 2022 | Fine-grained Attributed Graph Clustering | SDM | Link | Link |
| 2022 | Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation | NN | Link | Link |
| 2022 | SAGES: Scalable Attributed Graph Embedding with Sampling for Unsupervised Learning | TKDE | Link | - |
| 2022 | Automated Self-Supervised Learning For Graphs | ICLR | Link | Link |
| 2022 | Stationary diffusion state neural estimation for multi-view clustering | AAAI | Link | Link |
| 2021 | Simple Spectral Graph Convolution | ICLR | Link | Link |
| 2021 | Spectral embedding network for attributed graph clustering (SENet) | NN | Link | - |
| 2021 | Smoothness Sensor: Adaptive Smoothness Transition Graph Convolutions for Attributed Graph Clustering | TCYB | Link | Link |
| 2021 | Multi-view Attributed Graph Clustering | TKDE | Link | Link |
| 2021 | High-order Deep Multiplex Infomax | WWW | Link | Link |
| 2021 | Graph InfoClust: Maximizing Coarse-Grain Mutual Information in Graphs | PAKDD | Link | Link |
| 2021 | Graph Filter-based Multi-view Attributed Graph Clustering | IJCAI | Link | Link |
| 2021 | Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs | arXiv | Link | Link |
| 2021 | Contrastive Laplacian Eigenmaps | NeurIPS | Link | Link |
| 2020 | Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning | arXiv | Link | - |
| 2020 | Distribution-induced Bidirectional GAN for Graph Representation Learning | CVPR | Link | Link |
| 2020 | Adaptive Graph Converlutional Network with Attention Graph Clustering for Co saliency Detection | CVPR | Link | Link |
| 2020 | Spectral Clustering with Graph Neural Networks for Graph Pooling (MinCutPool) | ICML | Link | Link |
| 2020 | MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding | WWW | Link | Link |
| 2020 | Unsupervised Attributed Multiplex Network Embedding | AAAI | Link | Link |
| 2020 | Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure | ICDM | Link | Link |
| 2020 | Multi-class imbalanced graph convolutional network learning | IJCAI | Link | - |
| 2020 | CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning | arXiv | Link | - |
| 2020 | Attributed Graph Clustering via Deep Adaptive Graph Maximization | ICCKE | Link | - |
| 2019 | Heterogeneous Graph Attention Network (HAN) | WWW | Link | Link |
| 2019 | Multi-view Consensus Graph Clustering | TIP | Link | Link |
| 2019 | Attributed Graph Clustering via Adaptive Graph Convolution (AGC) | IJCAI | Link | Link |
| 2016 | node2vec: Scalable Feature Learning for Networks (node2vec) | SIGKDD | Link | Link |
| 2015 | LINE: Large-scale Information Network Embedding (LINE) | WWW | Link | Link |
| 2014 | DeepWalk: Online Learning of Social Representations (DeepWalk) | SIGKDD | Link | Link |
| 2016 | Variational Graph Auto-Encoders (GAE) | NeurIPS Workshop | Link | Link |
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
- load_graph_data: load graph datasets
- load_data: load non-graph datasets
- normalize_adj: normalize the adjacency matrix
- diffusion_adj: calculate the graph diffusion
- construct_graph: construct the knn graph for non-graph datasets
- numpy_to_torch: convert numpy to torch
- torch_to_numpy: convert torch to numpy
- clustering.py
- setup_seed: fix the random seed
- evaluation: evaluate the performance of clustering
- k_means: K-means algorithm
- visualization.py
- t_sne: t-SNE algorithm
- similarity_plot: visualize cosine similarity matrix of the embedding or feature
Datasets Details
About the introduction of each dataset, please check here
-
Graph Datasets
Dataset # Samples # Dimension # Edges # Classes URL CORA 2708 1433 5278 7 cora.zip CITESEER 3327 3703 4552 6 citeseer.zip CITE 3327 3703 4552 6 cite.zip PUBMED 19717 500 44324 3 pubmed.zip DBLP 4057 334 3528 4 dblp.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 17 wiki.zip COCS 18333 6805 81894 15 cocs.zip CORNELL 183 1703 149 5 cornell.zip TEXAS 183 1703 162 5 texas.zip WISC 251 1703 257 5 wisc.zip FILM 7600 932 15009 5 film.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.
-
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
@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}
}
@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{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}
}
@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}
}
Other Related Awesome Repository
Awesome Incomplete Graph Representation Learning
Awesome Knowledge Graph Reasoning