ABSTRACT
Incomplete multi-view clustering is a challenging task which aims to partition the unlabeled incomplete multi-view data into several clusters. The existing incomplete multi-view clustering methods neglect to utilize the diversified correlations inherent in data and handle the noise contained in different views. To address these issues, we propose a Robust Diversified Graph Contrastive Network (RDGC) for incomplete multi-view clustering, which integrates multi-view representation learning and diversified graph contrastive regularization into a unified framework. Multi-view unified and specific encoding network is developed to fuse different views into a unified representation, which can flexibly estimate the importance of views for incomplete multi-view data. Robust diversified graph contrastive regularization is proposed which captures the diversified data correlations to improve the discriminating power of the learned representation and reduce the information loss caused by the view missing problem. Moreover, our method can effectively resist the influence of noise and unreliable views by leveraging the robust contrastive learning loss. Extensive experiments conducted on four multi-view clustering datasets demonstrate the superiority of our method over the state-of-the-art methods.
- Arthur Asuncion and David Newman. 2007. UCI machine learning repository.Google Scholar
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607.Google Scholar
- Yongyong Chen, Xiaolin Xiao, Chong Peng, Guangming Lu, and Yicong Zhou. 2022. Low-Rank Tensor Graph Learning for Multi-View Subspace Clustering. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, 1 (2022), 92--104. https://doi.org/10.1109/TCSVT.2021.3055625Google ScholarDigital Library
- Ching-Yao Chuang, R Devon Hjelm, Xin Wang, Vibhav Vineet, Neel Joshi, Antonio Torralba, Stefanie Jegelka, and Yale Song. 2022. Robust Contrastive Learning against Noisy Views. CVPR (2022).Google Scholar
- Menglei Hu and Songcan Chen. 2019a. Doubly aligned incomplete multi-view clustering. arXiv preprint arXiv:1903.02785 (2019).Google Scholar
- Menglei Hu and Songcan Chen. 2019b. One-pass incomplete multi-view clustering. In AAAI, Vol. 33. 3838--3845.Google ScholarDigital Library
- Sung Ju Hwang and Kristen Grauman. 2010. Accounting for the relative importance of objects in image retrieval.. In BMVC, Vol. 1. 5.Google Scholar
- Yann LeCun. 1998. The MNIST database of handwritten digits. http://yann. lecun. com/exdb/mnist/ (1998).Google Scholar
- Lusi Li, Zhiqiang Wan, and Haibo He. 2021b. Incomplete Multi-view Clustering with Joint Partition and Graph Learning. IEEE Transactions on Knowledge and Data Engineering (2021), 1--1. https://doi.org/10.1109/TKDE.2021.3082470Google ScholarCross Ref
- Shao-Yuan Li, Yuan Jiang, and Zhi-Hua Zhou. 2014. Partial multi-view clustering. In Proceedings of the AAAI conference on artificial intelligence, Vol. 28.Google ScholarCross Ref
- Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, and Xi Peng. 2021a. Contrastive clustering. In 2021 AAAI Conference on Artificial Intelligence (AAAI).Google ScholarCross Ref
- Zhenglai Li, Chang Tang, Xiao Zheng, Xinwang Liu, Wei Zhang, and En Zhu. 2022. High-Order Correlation Preserved Incomplete Multi-View Subspace Clustering. IEEE Transactions on Image Processing , Vol. 31 (2022), 2067--2080.Google ScholarCross Ref
- Yijie Lin, Yuanbiao Gou, Zitao Liu, Boyun Li, Jiancheng Lv, and Xi Peng. 2021. COMPLETER: Incomplete multi-view clustering via contrastive prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11174--11183.Google ScholarCross Ref
- Jianlun Liu, Shaohua Teng, Lunke Fei, Wei Zhang, Xiaozhao Fang, Zhuxiu Zhang, and Naiqi Wu. 2021. A novel consensus learning approach to incomplete multi-view clustering. Pattern Recognition , Vol. 115 (2021), 107890.Google ScholarCross Ref
- Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, Chang Tang, Jianping Yin, Dinggang Shen, Huaimin Wang, and Wen Gao. 2019a. Late Fusion Incomplete Multi-View Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 41, 10 (2019), 2410--2423. https://doi.org/10.1109/TPAMI.2018.2879108Google ScholarDigital Library
- Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, En Zhu, Tongliang Liu, Marius Kloft, Dinggang Shen, Jianping Yin, and Wen Gao. 2019b. Multiple Kernel $ k $ k-Means with Incomplete Kernels. IEEE TPAMI, Vol. 42, 5 (2019), 1191--1204.Google Scholar
- Sherjil Ozair, Corey Lynch, Yoshua Bengio, Aaron van den Oord, Sergey Levine, and Pierre Sermanet. 2019. Wasserstein Dependency Measure for Representation Learning.Google Scholar
- Erlin Pan and Zhao Kang. 2021. Multi-view Contrastive Graph Clustering. Advances in Neural Information Processing Systems , Vol. 34 (2021).Google Scholar
- N. Rasiwasia, J. Costa Pereira, E. Coviello, G. Doyle, G.R.G. Lanckriet, R. Levy, and N. Vasconcelos. 2010. A New Approach to Cross-Modal Multimedia Retrieval. In ACM Multimedia. 251--260.Google Scholar
- Daniel J Trosten, Sigurd Lokse, Robert Jenssen, and Michael Kampffmeyer. 2021. Reconsidering Representation Alignment for Multi-view Clustering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1255--1265.Google ScholarCross Ref
- Aaron Van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv e-prints (2018), arXiv--1807.Google Scholar
- Hao Wang, Linlin Zong, Bing Liu, Yan Yang, and Wei Zhou. 2019. Spectral perturbation meets incomplete multi-view data. arXiv preprint arXiv:1906.00098 (2019).Google Scholar
- Qianqian Wang, Zhengming Ding, Zhiqiang Tao, Quanxue Gao, and Yun Fu. 2018. Partial multi-view clustering via consistent GAN. In ICDM. IEEE, 1290--1295.Google Scholar
- Qianqian Wang, Zhengming Ding, Zhiqiang Tao, Quanxue Gao, and Yun Fu. 2021. Generative Partial Multi-View Clustering With Adaptive Fusion and Cycle Consistency. IEEE Transactions on Image Processing , Vol. 30 (2021), 1771--1783.Google ScholarCross Ref
- Jie Wen, Zheng Zhang, Yong Xu, Bob Zhang, Lunke Fei, and Hong Liu. 2019. Unified embedding alignment with missing views inferring for incomplete multi-view clustering. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 5393--5400.Google ScholarDigital Library
- Jie Wen, Zheng Zhang, Yong Xu, Bob Zhang, Lunke Fei, and Guo-Sen Xie. 2021a. Cdimc-net: Cognitive deep incomplete multi-view clustering network. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 3230--3236.Google Scholar
- Jie Wen, Zheng Zhang, Zhao Zhang, Lunke Fei, and Meng Wang. 2020a. Generalized incomplete multiview clustering with flexible locality structure diffusion. IEEE transactions on cybernetics , Vol. 51, 1 (2020), 101--114.Google Scholar
- Jie Wen, Zheng Zhang, Zhao Zhang, Zhihao Wu, Lunke Fei, Yong Xu, and Bob Zhang. 2020b. DIMC-net: Deep Incomplete Multi-view Clustering Network. In Proceedings of the 28th ACM International Conference on Multimedia. 3753--3761.Google ScholarDigital Library
- Jie Wen, Zheng Zhang, Zhao Zhang, Lei Zhu, Lunke Fei, Bob Zhang, and Yong Xu. 2021b. Unified Tensor Framework for Incomplete Multi-view Clustering and Missing-view Inferring. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 10273--10281.Google ScholarCross Ref
- Cai Xu, Ziyu Guan, Wei Zhao, Hongchang Wu, Yunfei Niu, and Beilei Ling. 2019. Adversarial Incomplete Multi-view Clustering.. In IJCAI. 3933--3939.Google Scholar
- Jie Xu, Huayi Tang, Yazhou Ren, Xiaofeng Zhu, and Lifang He. 2021. Contrastive Multi-Modal Clustering. arXiv preprint arXiv:2106.11193 (2021).Google Scholar
- Zhe Xue, Junping Du, Dawei Du, and Siwei Lyu. 2019a. Deep low-rank subspace ensemble for multi-view clustering. Information Sciences , Vol. 482 (2019), 210--227.Google ScholarDigital Library
- Zhe Xue, Junping Du, Dawei Du, Wenqi Ren, and Siwei Lyu. 2019b. Deep Correlated Predictive Subspace Learning for Incomplete Multi-View Semi-Supervised Classification.. In IJCAI. 4026--4032.Google Scholar
- Zhe Xue, Junping Du, Changwei Zheng, Jie Song, Wenqi Ren, and Meiyu Liang. 2021. Clustering-Induced Adaptive Structure Enhancing Network for Incomplete Multi-View Data. In IJCAI. 3235--3241.Google Scholar
- Mouxing Yang, Yunfan Li, Zhenyu Huang, Zitao Liu, Peng Hu, and Xi Peng. 2021. Partially view-aligned representation learning with noise-robust contrastive loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1134--1143.Google ScholarCross Ref
- Changqing Zhang, Yajie Cui, Zongbo Han, Joey Tianyi Zhou, Huazhu Fu, and Qinghua Hu. 2020a. Deep partial multi-view learning. IEEE transactions on pattern analysis and machine intelligence (2020).Google Scholar
- Changqing Zhang, Huazhu Fu, Jing Wang, Wen Li, Xiaochun Cao, and Qinghua Hu. 2020b. Tensorized multi-view subspace representation learning. International Journal of Computer Vision , Vol. 128, 8 (2020), 2344--2361.Google ScholarDigital Library
- Handong Zhao, Hongfu Liu, and Yun Fu. 2016. Incomplete multi-modal visual data grouping.. In IJCAI. 2392--2398.Google Scholar
- Huasong Zhong, Jianlong Wu, Chong Chen, Jianqiang Huang, Minghua Deng, Liqiang Nie, Zhouchen Lin, and Xian-Sheng Hua. 2021. Graph Contrastive Clustering. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 9224--9233.Google ScholarCross Ref
- Pengfei Zhu, Xinjie Yao, Yu Wang, Meng Cao, Binyuan Hui, Shuai Zhao, and Qinghua Hu. 2022. Latent Heterogeneous Graph Network for Incomplete Multi-View Learning. IEEE Transactions on Multimedia (2022), 1--1. https://doi.org/10.1109/TMM.2022.3154592Google ScholarDigital Library
Index Terms
- Robust Diversified Graph Contrastive Network for Incomplete Multi-view Clustering
Recommendations
Joint learning of data recovering and graph contrastive denoising for incomplete multi-view clustering
AbstractIncomplete multi-view clustering is pivotal in machine learning because complex systems are inherently difficult to be fully observed and therefore pose a great challenge to revealing the mechanisms and structure of underlying systems. Current ...
Highlights- UGCF integrates data recovery, feature learning, and contrastive denoising for IMC.
- UGCF introduces a graph contrastive constraint, ensuring the compactness of features.
- UGCF removes the heterogeneity and noise of views by ...
Simultaneous Laplacian embedding and subspace clustering for incomplete multi-view data
AbstractIn many real multi-view data, some views often lose some information, resulting in incomplete views. It is a challenging task to extract and fuse valuable information from the multi-view data with incomplete views for improving clustering ...
Highlights- A novel incomplete multi-view subspace clustering method (SLESC) is proposed.
- The SLESC integrates multiple learning processes into a unified framework.
- The SLESC fuses multiple Laplacian embeddings for incomplete multi-view data.
Self-Augmentation Graph Contrastive Learning for Multi-view Attribute Graph Clustering
AMC-SME '23: Proceedings of the 2023 Workshop on Advanced Multimedia Computing for Smart Manufacturing and EngineeringMulti-view attribute graph clustering is a fundamental task which aims to partition multi-view attributes into multiple clusters in an unsupervised manner. The existing multi-view attribute graph clustering methods lack the utilization of comprehensive ...
Comments