GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Multi-view clustering can partition data samples into their categories by learning a consensus representation in unsupervised way and has received more and more attention in recent years. However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples. In this paper, we propose a novel multi-view clustering network to address these problems, called Global and Cross-view Feature Aggregation for Multi-View Clustering (GCFAggMVC). Specifically, the consensus data presentation from multiple views is obtained via cross-sample and cross-view feature aggregation, which fully explores the complementary of similar samples. Moreover, we align the consensus representation and the view-specific representation by the structure-guided contrastive learning module, which makes the view-specific representations from different samples with high structure relationship similar. The proposed module is a flexible multi-view data representation module, which can be also embedded to the incomplete multi-view data clustering task via plugging our module into other frameworks. Extensive experiments show that the proposed method achieves excellent performance in both complete multi-view data clustering tasks and incomplete multi-view data clustering tasks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We pre-train the models for 200 epochs for the reconstruction loss and then fine-tune the model for 100 epochs on mini-batches of size 256 using the Adam optimizer [22] in the PyTorch [34] framework.”
MethodExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
(2008) · Journal of Machine Learning Research · Cited by 33,051
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Fei-Fei, L., Fergus, R., & Perona, P. (2005) · 2004 Conference on Computer Vision and Pattern Recognition Workshop · doi:10.1109/cvpr.2004.383 · Cited by 2,502
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Co-regularized Multi-view Spectral Clustering
Kumar, A., Rai, P., & Daumé, H. (2011) · neural information processing systems · Cited by 1,467
Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models
Hershey, J. R., & Olsen, P. A. (2007) · 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 · doi:10.1109/icassp.2007.366913 · Cited by 1,189 · cited 1×
“For example, some methods align the representation distributions or label distributions from different views by KL divergence [14].”
MethodInformation Theory, Inference, and Learning Algorithms
(2004) · IEEE Transactions on Information Theory · doi:10.1109/tit.2004.834752 · Cited by 866 · cited 1×
“For the clustering module, we take the k-means [2,31] to obtain the clustering results for all samples.”
MethodDiversity-induced Multi-view Subspace Clustering
Cao, X., Zhang, C., Fu, H., Liu, S., & Zhang, H. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298657 · Cited by 835 · cited 1×
“For subspace-based multiview clustering [5, 13, 20, 30, 37, 45], they learn a consensus subspace self-representation matrix from each view, and partition the data points into different subspaces by applying different regularization terms on the consensus self-representation matrix.”
MethodMulti-view Subspace Clustering
Gao, H., Nie, F., Li, X., & Huang, H. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.482 · Cited by 614 · cited 1×
“For subspace-based multiview clustering [5, 13, 20, 30, 37, 45], they learn a consensus subspace self-representation matrix from each view, and partition the data points into different subspaces by applying different regularization terms on the consensus self-representation matrix.”
MethodSelf-weighted Multiview Clustering with Multiple Graphs
Nie, F., Li, J., & Li, X. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/357 · Cited by 562 · cited 1×
“For multiview graph clustering [11, 16, 19, 28, 32, 33], they generally do the following steps: construct viewspecific graphs, and then obtain a fusion graph by different regularization terms from multiple view-specific graphs, last, produce the clustering results by spectral clustering or graph-cut methods or other a…”
MethodCOMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction
Lin, Y., Gou, Y., Liu, Z., Li, B., Lv, J., & Peng, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01102 · Cited by 442
A Survey on Multiview Clustering
Chao, G., Sun, S., & Bi, J. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3065894 · Cited by 427
Multi-level Feature Learning for Contrastive Multi-view Clustering
Xu, J., Tang, H., Ren, Y., Peng, L., Zhu, X., & He, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01558 · Cited by 395
Consensus Graph Learning for Multi-View Clustering
Li, Z., Tang, C., Liu, X., Zheng, X., Zhang, W., & Zhu, E. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3081930 · Cited by 347
Self-citationJiang, Y.-G., Ye, G., Chang, S.-F., Ellis, D., & Loui, A. C. (2011) · Proceedings of the 1st ACM International Conference on Multimedia Retrieval · doi:10.1145/1991996.1992025 · Cited by 324 · cited 1×
“Prokaryotic [3] 551 3 4 Synthetic3d [23] 600 3 3 MNIST-USPS [35] 5000 2 10 CCV [18] 6773 3 20 Hdigit [7] 10000 2 10 Cifar10 1 50000 3 10 Cifar100 2 50000 3 100 YouTubeFace3 101499 5 31 Caltech-5V [12] 1400 5 7 NGs 4 500 3 5 Cora [47] 2708 2 7 BDGP [4] 2500 2 5 Fashion [48] 10000 3 10”
Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion
Wen, J., Zhang, Z., Zhang, Z., Fei, L., & Wang, M. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2987164 · Cited by 305
Fast Multi-View Clustering Via Ensembles: Towards Scalability, Superiority, and Simplicity
Huang, D., Wang, C., & Lai, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3236698 · Cited by 289 · cited 2×
“Specifically, we obtain the following observations: (1) Our method obtains better results than four traditional multiview clustering methods (PLCMF, LMVSC, SMVSC, and FastMICE).”
MethodExclusivity-Consistency Regularized Multi-view Subspace Clustering
Wang, X., Guo, X., Lei, Z., Zhang, C., & Li, S. Z. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.8 · Cited by 281 · cited 1×
“For subspace-based multiview clustering [5, 13, 20, 30, 37, 45], they learn a consensus subspace self-representation matrix from each view, and partition the data points into different subspaces by applying different regularization terms on the consensus self-representation matrix.”
MethodSelf-Supervised Video Hashing With Hierarchical Binary Auto-Encoder
Song, J., Zhang, H., Li, X., Gao, L., Wang, M., & Hong, R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2814344 · Cited by 276 · cited 1×
“In particular, autoencoder [15, 36] is a widely used unsupervised model that projects original data features into a designed feature space.”
MethodDeep embedded multi-view clustering with collaborative training
Xu, J., Ren, Y., Li, G., Pan, L., Zhu, C., & Xu, Z. (2021) · Information Sciences · doi:10.1016/j.ins.2020.12.073 · Cited by 269 · cited 1×
“The former includes 4 traditional methods (PLCMF [43], LMVSC [20], SMVSC [37], and FastMICE [17]) and 5 deep methods (DEMVC [50], CONAN [21], SiMVC [40], CoMVC [40], MFLVC [51]).”
MethodCOMIC: Multi-view Clustering Without Parameter Selection
Peng, X., Huang, Z., Lv, J., Zhu, H., & Zhou, J. T. (2019) · International Conference on Machine Learning · Cited by 265
Multi-view Attributed Graph Clustering
Lin, Z., Kang, Z., Zhang, L., & Tian, L. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3101227 · Cited by 253 · cited 1×
“For multiview graph clustering [11, 16, 19, 28, 32, 33], they generally do the following steps: construct viewspecific graphs, and then obtain a fusion graph by different regularization terms from multiple view-specific graphs, last, produce the clustering results by spectral clustering or graph-cut methods or other a…”
MethodReconsidering Representation Alignment for Multi-view Clustering
Trosten, D. J., Lokse, S., Jenssen, R., & Kampffmeyer, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00131 · Cited by 226 · cited 6×
“In DEMVC, they consider to align label distributions of different views to a target distribution, which has a negative impact since a given cluster distribution from one view might be aligned with a different cluster distribution from another view [40].”
BackgroundMethodInfluentialDeep Incomplete Multi-View Clustering via Mining Cluster Complementarity
Xu, J., Li, C., Ren, Y., Peng, L., Mo, Y., Shi, X., & Zhu, X. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20856 · Cited by 188
Deep Multimodal Subspace Clustering Networks
Abavisani, M., & Patel, V. M. (2018) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2018.2875385 · Cited by 181
Deep Adversarial Multi-view Clustering Network
Li, Z., Wang, Q., Tao, Z., Gao, Q., & Yang, Z. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/409 · Cited by 166 · cited 1×
“Some deep multi-view clustering methods [24,26,44,52] use adversarial training to learn the latent feature representations and align distributions of hidden representations from different views.”
BackgroundEnd-to-End Adversarial-Attention Network for Multi-Modal Clustering
Zhou, R., & Shen, Y.-D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01463 · Cited by 166 · cited 2×
“[52] leveraged the attention mechanism to obtain a weight value for each view, and obtained a consensus representation by weight summation of all view-wise presentations.”
BackgroundMethodJoint stage recognition and anatomical annotation of drosophila gene expression patterns
Cai, X., Wang, H., Huang, H., & Ding, C. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts220 · Cited by 163 · cited 2×
“Prokaryotic [3] 551 3 4 Synthetic3d [23] 600 3 3 MNIST-USPS [35] 5000 2 10 CCV [18] 6773 3 20 Hdigit [7] 10000 2 10 Cifar10 1 50000 3 10 Cifar100 2 50000 3 100 YouTubeFace3 101499 5 31 Caltech-5V [12] 1400 5 7 NGs 4 500 3 5 Cora [47] 2708 2 7 BDGP [4] 2500 2 5 Fashion [48] 10000 3 10”
Representation Learning in Multi-view Clustering: A Literature Review
Chen, M.-S., Lin, J.-Q., Li, X.-L., Liu, B.-Y., Wang, C.-D., Huang, D., & Lai, J.-H. (2022) · Data Science and Engineering · doi:10.1007/s41019-022-00190-8 · Cited by 163
CDIMC-net: Cognitive Deep Incomplete Multi-view Clustering Network
Wen, J., Zhang, Z., Xu, Y. D., Zhang, B., Fei, L., & Xie, G.-S. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/447 · Cited by 154
The landscape of microbial phenotypic traits and associated genes
Brbić, M., Piškorec, M., Vidulin, V., Kriško, A., Šmuc, T., & Supek, F. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkw964 · Cited by 149
Multi-view spectral clustering via sparse graph learning
Hu, Z., Nie, F., Chang, W., Hao, S., Wang, R., & Li, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.12.004 · Cited by 125 · cited 1×
“For multiview graph clustering [11, 16, 19, 28, 32, 33], they generally do the following steps: construct viewspecific graphs, and then obtain a fusion graph by different regularization terms from multiple view-specific graphs, last, produce the clustering results by spectral clustering or graph-cut methods or other a…”
MethodAdversarial Multiview Clustering Networks With Adaptive Fusion
Wang, Q., Tao, Z., Xia, W., Gao, Q., Cao, X., & Jiao, L. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3145048 · Cited by 123 · cited 2×
“[44] obtained the consensus representation by a weight summation and l1,2norm constraint.”
BackgroundMethodMulti-view subspace clustering via partition fusion
Lv, J., Kang, Z., Wang, B., Ji, L., & Xu, Z. (2021) · Information Sciences · doi:10.1016/j.ins.2021.01.033 · Cited by 121
Deep Multiple Auto-Encoder-Based Multi-view Clustering
Du, G., Zhou, L., Yang, Y., Lü, K., & Wang, L. (2021) · Data Science and Engineering · doi:10.1007/s41019-021-00159-z · Cited by 93
CONAN: Contrastive Fusion Networks for Multi-view Clustering
Ke, G., Hong, Z., Zeng, Z., Liu, Z., Sun, Y., & Xie, Y. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671851 · Cited by 86 · cited 4×
“In CONAN, SiMVC, and CoMVC, they obtain a consensus feature representation by view-wise fusion method.”
MethodInfluentialPseudo-Label Guided Collective Matrix Factorization for Multiview Clustering
Wang, D., Han, S., Wang, Q., He, L., Tian, Y., & Gao, X. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3051182 · Cited by 82 · cited 1×
“The former includes 4 traditional methods (PLCMF [43], LMVSC [20], SMVSC [37], and FastMICE [17]) and 5 deep methods (DEMVC [50], CONAN [21], SiMVC [40], CoMVC [40], MFLVC [51]).”
MethodStructure-Preserving Graph Representation Learning
Fang, R., Wen, L., Kang, Z., & Liu, J. (2022) · Proceedings · doi:10.1109/icdm54844.2022.00109 · Cited by 53 · cited 1×
“For multiview graph clustering [11, 16, 19, 28, 32, 33], they generally do the following steps: construct viewspecific graphs, and then obtain a fusion graph by different regularization terms from multiple view-specific graphs, last, produce the clustering results by spectral clustering or graph-cut methods or other a…”
MethodMulti-view clustering via adversarial view embedding and adaptive view fusion
Li, Y., & Liao, H. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01864-4 · Cited by 22
Metadata
- Authors
- Yan, W., Zhang, Y., Lv, C., Tang, C., Yue, G., Liao, L., & Lin, W.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 19863-19872
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386071520
- Cited by
- 197
- References
- 44
- FWCI
- 37.24
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.