Home

Awesome

Awesome-Deep-Multi-View-Clustering

Collections for state-of-the-art and novel deep neural network-based multi-view clustering approaches (papers & codes). According to the integrity of multi-view data, such methods can be further subdivided into Deep Multi-view Clustering(DMVC) and Deep Incomplete Multi-view Clustering(DIMVC).

We are looking forward for other participants to share their papers and codes. If interested or any question about the listed papers and codes, please contact jinjiaqi@nudt.edu.cn. 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 1-2 papers in the citation part here. :heart:

GitHub stars GitHub forks

Table of Contents


<span id="jump1">What's Deep Multi-view Clustering? </span>

Deep multi-view clustering aims to reveal the potential complementary information of multiple features or modalities through deep neural networks, and finally divide samples into different groups in unsupervised scenarios.

<div align="center"> <img src="./DMVC_frame.png" width=70% /> </div>

<span id="jump2">Surveys </span>

YearTitleVenuePaper
2024A Survey and an Empirical Evaluation of Multi-view Clustering ApproachesACM CS
2024Self‐Supervised Multi‐View Clustering in Computer Vision: A SurveyIET CV
2024The Methods for Improving Large-Scale Multi-View Clustering Efficiency: A SurveyAIR
2024Deep Clustering:A Comprehensive SurveyTNNLS
2024Breaking Down Multi-view Clustering:A Comprehensive Review of Multi-view Approaches for Complex Data StructuresEAAI
2024Incomplete Multi-view Learning: Review, Analysis, and ProspectsASC
2023A Comprehensive Survey on Multi-view ClusteringTKDE
2022Representation Learning in Multi-view Clustering: A Literature ReviewDSE
2022Foundations and Recent Trends in Multimodal Machine Learning: Principles, Challenges, and Open QuestionsArxiv
2021Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry, and FusionTOMM
2021Deep Multi-view Learning Methods: A ReviewNeurocom
2018A Survey of Multi-View Representation LearningTKDE
2018Multi-view Clustering: A SurveyBDMA
2018Multimodal Machine Learning: A Survey and TaxonomyTPAMI
2018A Survey on Multi-View ClusteringArxiv
2017Multi-view Learning Overview:Recent Progress and New ChallengesIF
2013A Survey on Multi-view LearningArxiv

<span id="jump3">Papers & Codes </span>

According to the integrity of multi-view data, the paper is divided into deep multi-view clustering methods and deep incomplete multi-view clustering approaches.

<span id="jump31">Deep Multi-view Clustering(DMVC)</span>

YearTitleAbbreviationVenuePaperCode
2024Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense FrameworkAR-DMVC-AMICML
2024Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid ViewsFMCSCNeurIPS
2024Robust Contrastive Multi-view Clustering against Dual Noisy CorrespondenceCANDYNeurIPS
2024Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view ClusteringSCE-MVCNeurIPS-
2024Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View ScenariosMVCANCVPR
2024Rethinking Multi-view Representation Learning via Distilled DisentanglingMRDDCVPR
2024Differentiable Information Bottleneck for Deterministic Multi-view ClusteringDIBCVPR-
2024Deep Generative Clustering with Multimodal Diffusion Variational AutoencodersCMVAEICLR-
2024Learning Common Semantics via Optimal Transport for Contrastive Multi-view ClusteringCSOTTIP
2024Dual Contrast-Driven Deep Multi-View ClusteringDCMVCTIP
2024Multiview Deep Subspace Clustering NetworksMvDSCNTCYB-
2024Deep Contrastive Multi-View Subspace Clustering With Representation and Cluster Interactive LearningDCMVSCTKDE-
2024Robust Multi-View Clustering with Noisy CorrespondenceRMCNCTKDE
2024Integrating Vision-Language Semantic Graphs in Multi-View ClusteringIVSGMVIJCAI-
2024Simple Contrastive Multi-View Clustering with Data-Level FusionSCMIJCAI
2024Dynamic Weighted Graph Fusion for Deep Multi-View ClusteringDFMVCIJCAI-
2024Contrastive and View-Interaction Structure Learning for Multi-view ClusteringSERIESIJCAI-
2024Active Deep Multi-view ClusteringADMCIJCAI
2024Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph ClusteringAHGFCAAAI-
2024SURER: Structure-Adaptive Unified Graph Neural Network for Multi-View ClusteringSURERAAAI
2024Heterogeneity-Aware Federated Deep Multi-View Clustering towards Diverse Feature RepresentationsHFMVCACM MM
2024EMVCC: Enhanced Multi-View Contrastive Clustering for Hyperspectral ImagesEMVCCACM MM
2024DFMVC: Deep Fair Multi-view ClusteringDFMVCACM MM-
2024View Gap Matters: Cross-view Topology and Information Decoupling for Multi-view ClusteringTGM-MVCACM MM-
2024Learning Dual Enhanced Representation for Contrastive Multi-view ClusteringLUCE-CMCACM MM
2024Contrastive Graph Distribution Alignment for Partially View-Aligned ClusteringCGDAACM MM-
2024Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph ClusteringDOAGCACM MM-
2024Robust Variational Contrastive Learning for Partially View-unaligned ClusteringVITALACM MM
2024Self-Weighted Contrastive Fusion for Deep Multi-View ClusteringSCMVCTMM
2024Subspace-Contrastive Multi-View ClusteringSCMCTKDD-
2024Multi-view contrastive clustering via integrating graph aggregation and confidence enhancementMAGAIF
2024Trustworthy multi-view clustering via alternating generative adversarial representation learning and fusionAGARLIF-
2024Structural deep multi-view clustering with integrated abstraction and detailSMVCNN-
2024Progressive Neighbor-masked Contrastive Learning for Fusion-style Deep Multi-View ClusteringPNCL-FDMCNN-
2024Composite Attention Mechanism Network for Deep Contrastive Multi-view ClusteringCAMVCNN-
2024Asymmetric Double-Winged Multi-View Clustering Network for Exploring Diverse and Consistent InformationCodingNetNN-
2024Decomposed deep multi-view subspace clustering with self-labeling supervisionD2MVSCIS-
2024Structure-guided feature and cluster contrastive learning for multi-view clusteringSGFCCNeurcom-
2024Learning consensus representations in multi-latent spaces for multi-view clusteringDMCCNeurcom-
2024MCoCo: Multi-level Consistency Collaborative Multi-view ClusteringMCoCoESA-
2024Graph-Driven Deep Multi-View Clustering with Self-Paced LearningGDMVCKBS
2024Information Bottleneck Fusion for Deep Multi-view ClusteringIBFDMVCKBS-
2024Separable Consistency and Diversity Feature Learning for Multi-View ClusteringSCDFLSPL-
2023Graph Embedding Contrastive Multi-Modal Representation Learning for ClusteringGECMCTIP
2023Neighbor-aware deep multi-view clustering via graph convolutional networkNMvC-GCNIF
2023Joint contrastive triple-learning for deep multi-view clusteringJCTIPM
2023Auto-attention mechanism for multi-view deep embedding clusteringMDECPR-
2023Deep multi-view spectral clustering via ensembleDMCEPR-
2023Unified Representation Learning for Multi-View Clustering by Between/Within View Deep MajorizationdeepURLTETCI
2023Dropping pathways towards deep multi-view graph subspace clustering networksDPMGSCACM MM-
2023Triple-granularity contrastive learning for deep multi-view subspace clusteringTRUSTACM MM-
2023Deep multiview adaptive clustering with semantic invarianceDMAC-SITNNLS
2023Generalized Information-theoretic Multi-view ClusteringIMCNeurIPS-
2023Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation DegenerationSEMNeurIPS
2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic PerspectiveSUMVCNeurIPS
2023Dual Label-Guided Graph Refnement for Multi-View Graph ClusteringDuaLGRAAAI
2023Cross-view Topology Based Consistent and Complementary Information for Deep Multi-view ClusteringCTCCICCV-
2023MHCN: A Hyperbolic Neural Network Model for Multi-view Hierarchical ClusteringMHCNICCV-
2023Deep Multiview Clustering by Contrasting Cluster AssignmentsCVCLICCV
2023DealMVC: Dual Contrastive Calibration for Multi-view ClusteringDealMVCACM MM
2023Self-Supervised Graph Attention Networks for Deep Weighted Multi-View ClusteringSGDMCAAAI-
2023Dual Fusion-Propagation Graph Neural Network for Multi-view ClusteringDFP-GNNTMM-
2023Joint Shared-and-Specific Information for Deep Multi-View ClusteringJSSITCSVT-
2023On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view ClusteringDeepMVCCVPR
2023GCFAgg:Global and Cross-view Feature Aggregation for Multi-view ClusteringGCFAggCVPR-
2023Self-Supervised Information Bottleneck for Deep Multi-View Subspace ClusteringSIB-MSCTIP-
2023Multi-channel Augmented Graph Embedding Convolutional Network for Multi-view ClusteringMAGEC-NetTNSE-
2022Deep Safe Multi-View Clustering:Reducing the Risk of Clustering Performance Degradation Caused by View IncreaseDSMVCCVPR
2022Multi-level Feature Learning for Contrastive Multi-view ClusteringMFLVCCVPR
2022Stationary Diffusion State Neural Estimation for Multiview ClusteringSDSNEAAAI
2022Multi-View Subspace Clustering via Structured Multi-Pathway NetworkSMpNetTNNLS
2022Multiview Subspace Clustering With Multilevel Representations and Adversarial RegularizationMvSC-MRARTNNLS-
2022Self-Supervised Deep Multiview Spectral ClusteringSDMvSCTNNLS-
2022Contrastive Multi-view Hyperbolic Hierarchical ClusteringCMHHCIJCAI-
2022Multi-view Graph Embedding Clustering Network:Joint Self-supervision and Block Diagonal RepresentationMVGCNN
2022Efficient Multi‑view Clustering NetworksEMC-NetsAPPL INTELL
2021Deep Mutual Information Maximin for Cross-Modal ClusteringDMIMAAAI-
2021Uncertainty-Aware Multi-View Representation LearningDUA-NetsAAAI
2021Learning Deep Sparse Regularizers With Applications to Multi-View Clustering and Semi-Supervised ClassificationDSRLTPAMI
2021Reconsidering Representation Alignment for Multi-view ClusteringSiMVC&CoMVCCVPR
2021Deep Multiple Auto-Encoder-Based Multi-view ClusteringMVC_MAEDSE
2021Multimodal Clustering Networks for Self-supervised Learning from Unlabeled VideosMCNICCV
2021Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view ClusteringMulti-VAEICCV
2021Graph Filter-based Multi-view Attributed Graph ClusteringMvAGCIJCAI
2021Multi-view Subspace Clustering Networks with Local and Global Graph InformationMSCNGLNeurocom
2021Attentive Multi-View Deep Subspace Clustering NetAMVDSNNeurocom-
2021Multi-view Contrastive Graph ClusteringMCGCNeurIPS
2021Self-supervised Discriminative Feature Learning for Deep Multi-view ClusteringSDMVCTKDE
2021Multi-view Attributed Graph ClusteringMAGCTKDE
2021Deep Multi-view Subspace Clustering with Unified and Discriminative LearningDMSC-UDLTMM
2021Self-supervised Graph Convolutional Network for Multi-view ClusteringSGCMCTMM
2021Consistent Multiple Graph Embedding for Multi-View ClusteringCMGECTMM
2021Deep Multiview Collaborative ClusteringDMCCTNNLS-
2020Partially View-aligned ClusteringPVCNeurIPS
2020Cross-modal Subspace Clustering via Deep Canonical Correlation AnalysisCMSC-DCCAAAAI-
2020Shared Generative Latent Representation Learning for Multi-View ClusteringDMVCVAEAAAI
2020End-to-End Adversarial-Attention Network for Multi-Modal ClusteringEAMCCVPR
2020Multi-View Attribute Graph Convolution Networks for ClusteringMAGCNIJCAI
2020End-To-End Deep Multimodal ClusteringDMMCICME
2020Deep Embedded Multi-view Clustering with Collaborative TrainingDEMVCIS
2020Joint Deep Multi-View Learning for Image ClusteringDMJCTKDE-
2020One2Multi Graph Autoencoder for Multi-view Graph ClusteringO2MVCWWW
2019AE^2-Nets: Autoencoder in Autoencoder NetworksAE^2-NetsCVPR
2019COMIC: Multi-view Clustering Without Parameter SelectionCOMICICML
2019Deep Adversarial Multi-view Clustering NetworkDAMCIJCAI
2019Multi-view Spectral Clustering NetworkMvSCNIJCAI
2019Multi-view Deep Subspace Clustering NetworksMvDSCNTIP
2018Generalized Latent Multi-View Subspace ClusteringgLMSCTPAMI
2018Deep Multimodal Subspace Clustering NetworksDMSCSTSP
2018Deep Multi-View Clustering via Multiple EmbeddingDMVC-MECoRR-

<span id="jump32">Deep Incomplete Multi-view Clustering(DIMVC)</span>

YearTitleAbbreviationVenuePaperCode
2024Diffusion-based Missing-view Generation With the Application on Incomplete Multi-view ClusteringDMVGICML
2024Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering StructuresDVIMCAAAI
2024Partial Multi-View Clustering via Self-Supervised NetworkPVC-SCNAAAI-
2024Incomplete Contrastive Multi-View Clustering with High-Confidence GuidingICMVCAAAI
2024Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View ClusteringAGDIMCAAAI-
2024Decoupled Contrastive Multi-view Clustering with High-order Random WalksDIVIDEAAAI
2024Robust Prototype Completion for Incomplete Multi-view ClusteringRPCICACM MM
2024URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View ClusteringURRL-IMVCSIGKDD-
2024Subgraph Propagation and Contrastive Calibration for Incomplete Multiview Data ClusteringSPCCTNNLS-
2024Deep Incomplete Multiview Clustering via Local and Global Pseudo-Label PropagationPLP-IMVCTNNLS-
2024Robust Multi-Graph Contrastive Network for Incomplete Multi-View ClusteringRMGCTMM-
2024A novel Federated Multi-view Clustering Method for Unaligned and Incomplete Data FusionFUCIFIF
2024Contrastive and Adversarial Regularized Multi-level Representation Learning for Incomplete Multi-view ClusteringMRL_CALNN
2024View-interactive Attention Information Alignment-guided Fusion for Incomplete Multi-view ClusteringVAIAFESA-
2024Graph-Guided Imputation-Free Incomplete Multi-View ClusteringGIMVCESA
2024Deep Incomplete Multi-View Clustering via Attention-Based Direct Contrastive LearningADCLESA-
2024Incomplete Multi-View Clustering via Diffusion CompletionIMVCDCMTA-
2024Incomplete Multi-View Clustering Via Inference and EvaluationIMVC-IEICASSP
2024Incomplete Multi-view Clustering via Self-attention Networks and Feature ReconstructionSNFRAPPL INTELL-
2023UNTIE: Clustering Analysis with Disentanglement in Multi-view Information FusionUNTIEIF-
2023Federated Deep Multi-View Clustering with Global Self-SupervisionFedDMVCACM MM-
2023Incomplete Multi-view Clustering via Attention-based Contrast LearningMCACIJMLC
2023Incomplete Multi-View Clustering With Complete View GuidanceIMC-CVGSPL-
2023Information Recovery-driven Deep Incomplete Multiview Clustering NetworkRecFormerTNNLS
2023Realize Generative Yet Complete Latent Representation for Incomplete Multi-View LearningCMVAETPAMI-
2023Semantic Invariant Multi-View Clustering With Fully Incomplete InformationSMILETPAMI
2023Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype AlignmentCPSPANCVPR
2023Adaptive Feature Projection with Distribution Alignment for Deep Incomplete Multi-view ClusteringAPADCTIP
2023Incomplete Multi-view Clustering via Prototype-based ImputationProImpIJCAI
2023Consistent Graph Embedding Network with Optimal Transport for Incomplete Multi-view ClusteringCGEN-OTIS-
2023CCR-Net: Consistent Contrastive Representation Network for Multi-view ClusteringCCR-NetIS
2023Incomplete Multi-view Clustering Network via Nonlinear Manifold Embedding and Probability-Induced LossIMCNet-MPNN-
2022Robust Multi-view Clustering with Incomplete InformationSURETPAMI
2022Dual Contrastive Prediction for Incomplete Multi-view Representation LearningDCPTPAMI
2022Deep Safe Incomplete Multi-view Clustering: Theorem and AlgorithmDSIMVCICML
2022Deep Incomplete Multi-view Clustering via Mining Cluster ComplementarityDIMVCAAAI
2022Robust Diversified Graph Contrastive Network for Incomplete Multi-view ClusteringRDGCACM MM
2022Incomplete Multi-view Clustering via Cross-view Relation TransferCRTCTCSVT-
2022Graph Contrastive Partial Multi-view ClusteringAGCLTMM
2021COMPLETER: Incomplete Multi-view Clustering via Contrastive PredictionCOMPLETERCVPR
2021iCmSC: Incomplete Cross-modal Subspace ClusteringiCmSCTIP
2021Generative Partial Multi-View Clustering With Adaptive Fusion and Cycle ConsistencyGP-MVCTIP
2021Clustering-Induced Adaptive Structure Enhancing Network for Incomplete Multi-View DataCASENIJCAI-
2021Structural Deep Incomplete Multi-view Clustering NetworkSDIMC-netCIKM-
2021Dual Alignment Self-Supervised Incomplete Multi-View Subspace Clustering NetworkDASIMSCSPL-
2020Deep Partial Multi-View LearningDPMLTPAMI
2020CDIMC-net:Cognitive Deep Incomplete Multi-view Clustering Network(CDIMC-netIJCAI
2020DIMC-net:Deep Incomplete Multi-view Clustering NetworkDIMC-netACM MM-
2020Deep Incomplete Multi-View Multiple ClusteringsDiMVMCICDM
2019CPM-Nets: Cross Partial Multi-View NetworksCPM-NetsNeurIPS
2019Adversarial Incomplete Multi-view ClusteringAIMCIJCAI-
2018Partial Multi-View Clustering via Consistent GANPVC-GANICDM

<span id="jump4">Citation </span>

@inproceedings{jin2023deep,
  title={Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment},
  author={Jin, Jiaqi and Wang, Siwei and Dong, Zhibin and Liu, Xinwang and Zhu, En},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11600--11609},
  year={2023}
}

@inproceedings{wangevaluate,
  title={Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering},
  author={Wang, Fangdi and Jin, Jiaqi and Hu, Jingtao and Liu, Suyuan and Yang, Xihong and Wang, Siwei and Liu, Xinwang and Zhu, En},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}
}

@article{wang2022align,
  title={Align then fusion: Generalized large-scale multi-view clustering with anchor matching correspondences},
  author={Wang, Siwei and Liu, Xinwang and Liu, Suyuan and Jin, Jiaqi and Tu, Wenxuan and Zhu, Xinzhong and Zhu, En},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={5882--5895},
  year={2022}
}

@inproceedings{dong2023cross,
  title={Cross-view topology based consistent and complementary information for deep multi-view clustering},
  author={Dong, Zhibin and Wang, Siwei and Jin, Jiaqi and Liu, Xinwang and Zhu, En},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={19440--19451},
  year={2023}
}

@inproceedings{yang2023dealmvc,
  title={Dealmvc: Dual contrastive calibration for multi-view clustering},
  author={Yang, Xihong and Jiaqi, Jin and Wang, Siwei and Liang, Ke and Liu, Yue and Wen, Yi and Liu, Suyuan and Zhou, Sihang and Liu, Xinwang and Zhu, En},
  booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
  pages={337--346},
  year={2023}
}

@inproceedings{wang2024view,
  title={View Gap Matters: Cross-view Topology and Information Decoupling for Multi-view Clustering},
  author={Wang, Fangdi and Jin, Jiaqi and Dong, Zhibin and Yang, Xihong and Feng, Yu and Liu, Xinwang and Zhu, Xinzhong and Wang, Siwei and Liu, Tianrui and Zhu, En},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  pages={8431--8440},
  year={2024}
}

@article{dong2024subgraph,
  title={Subgraph Propagation and Contrastive Calibration for Incomplete Multiview Data Clustering},
  author={Dong, Zhibin and Jin, Jiaqi and Xiao, Yuyang and Xiao, Bin and Wang, Siwei and Liu, Xinwang and Zhu, En},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2024},
  publisher={IEEE}
}

@article{dong2023iterative,
  title={Iterative deep structural graph contrast clustering for multiview raw data},
  author={Dong, Zhibin and Jin, Jiaqi and Xiao, Yuyang and Wang, Siwei and Zhu, Xinzhong and Liu, Xinwang and Zhu, En},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2023},
  publisher={IEEE}
}