ABSTRACT
Benefiting from the strong view-consistent information mining capacity, multi-view contrastive clustering has attracted plenty of attention in recent years. However, we observe the following drawback, which limits the clustering performance from further improvement. The existing multi-view models mainly focus on the consistency of the same samples in different views while ignoring the circumstance of similar but different samples in cross-view scenarios. To solve this problem, we propose a novel Dual contrastive calibration network for Multi-View Clustering (DealMVC). Specifically, we first design a fusion mechanism to obtain a global cross-view feature. Then, a global contrastive calibration loss is proposed by aligning the view feature similarity graph and the high-confidence pseudo-label graph. Moreover, to utilize the diversity of multi-view information, we propose a local contrastive calibration loss to constrain the consistency of pair-wise view features. The feature structure is regularized by reliable class information, thus guaranteeing similar samples have similar features in different views. During the training procedure, the interacted cross-view feature is jointly optimized at both local and global levels. In comparison with other state-of-the-art approaches, the comprehensive experimental results obtained from eight benchmark datasets provide substantial validation of the effectiveness and superiority of our algorithm. We release the code of DealMVC at https://github.com/xihongyang1999/DealMVC on GitHub.
Supplemental Material
- Xiao Cai, Feiping Nie, and Heng Huang. 2013. Multi-view k-means clustering on big data. In Twenty-Third International Joint conference on artificial intelligence.Google ScholarDigital Library
- Peng Cao, Qingshan Hou, Ruoxian Song, Haonan Wang, and Osmar Zaiane. 2022. Collaborative learning of weakly-supervised domain adaptation for diabetic retinopathy grading on retinal images. Computers in Biology and Medicine 144 (2022), 105341.Google ScholarDigital Library
- Xiaochun Cao, Changqing Zhang, Huazhu Fu, Si Liu, and Hua Zhang. 2015. Diversity-induced multi-view subspace clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition. 586--594.Google ScholarCross Ref
- 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
- Jiafeng Cheng, QianqianWang, Zhiqiang Tao, Deyan Xie, and Quanxue Gao. 2021. Multi-view attribute graph convolution networks for clustering. In Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence. 2973--2979.Google Scholar
- Kaveh Hassani and Amir Hosein Khasahmadi. 2020. Contrastive multi-view representation learning on graphs. In International Conference on Machine Learning. PMLR, 4116--4126.Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9729--9738.Google ScholarCross Ref
- Rundong He, Zhongyi Han, Xiankai Lu, and Yilong Yin. 2022. Safe-student for safe deep semi-supervised learning with unseen-class unlabeled data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14585--14594.Google ScholarCross Ref
- Rundong He, Zhongyi Han, Yang Yang, and Yilong Yin. 2022. Not all parameters should be treated equally: Deep safe semi-supervised learning under class distribution mismatch. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 6874--6883.Google ScholarCross Ref
- Geoffrey E Hinton. 2002. Training products of experts by minimizing contrastive divergence. Neural computation 14, 8 (2002), 1771--1800.Google Scholar
- Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. science 313, 5786 (2006), 504--507.Google Scholar
- Qingshan Hou, Peng Cao, Liyu Jia, Leqi Chen, Jinzhu Yang, and Osmar R Zaiane. 2022. Image Quality Assessment Guided Collaborative Learning of Image Enhancement and Classification for Diabetic Retinopathy Grading. IEEE Journal of Biomedical and Health Informatics 27, 3 (2022), 1455--1466.Google ScholarCross Ref
- Xiaochang Hu, Xin Xu, Yujun Zeng, and Xihong Yang. 2023. Patch-Mixing Contrastive Regularization for Few-Label Semi-Supervised Learning. IEEE Transactions on Artificial Intelligence (2023), 1--14. https://doi.org/10.1109/TAI.2023. 3247975Google ScholarCross Ref
- Shudong Huang, Zhao Kang, and Zenglin Xu. 2020. Auto-weighted multi-view clustering via deep matrix decomposition. Pattern Recognition 97 (2020), 107015.Google ScholarDigital Library
- Aapo Hyvärinen and Peter Dayan. 2005. Estimation of non-normalized statistical models by score matching. Journal of Machine Learning Research 6, 4 (2005).Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Jian Li, Zhaopeng Tu, Baosong Yang, Michael R Lyu, and Tong Zhang. 2018. Multihead attention with disagreement regularization. arXiv preprint arXiv:1810.10183 (2018).Google Scholar
- Zhenglai Li, Chang Tang, Xinwang Liu, Xiao Zheng, Wei Zhang, and En Zhu. 2021. Consensus graph learning for multi-view clustering. IEEE Transactions on Multimedia 24 (2021), 2461--2472.Google ScholarDigital Library
- Zhaoyang Li, Qianqian Wang, Zhiqiang Tao, Quanxue Gao, Zhaohua Yang, et al. 2019. Deep Adversarial Multi-view Clustering Network.. In IJCAI. 2952--2958.Google Scholar
- Zhaoyang Li, Qianqian Wang, Zhiqiang Tao, Quanxue Gao, Zhaohua Yang, et al. 2019. Deep Adversarial Multi-view Clustering Network.. In IJCAI. 2952--2958.Google Scholar
- 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
- 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
- Chenghua Liu, Zhuolin Liao, Yixuan Ma, and Kun Zhan. 2022. Stationary diffusion state neural estimation for multiview clustering. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 7542--7549.Google ScholarCross Ref
- Jialu Liu, Chi Wang, Jing Gao, and Jiawei Han. 2013. Multi-view clustering via joint nonnegative matrix factorization. In Proceedings of the 2013 SIAM international conference on data mining. SIAM, 252--260.Google ScholarCross Ref
- Suyuan Liu, Xinwang Liu, Siwei Wang, Xin Niu, and En Zhu. 2022. Fast Incomplete Multi-View Clustering With View-Independent Anchors. IEEE Transactions on Neural Networks and Learning Systems (2022).Google ScholarCross Ref
- Suyuan Liu, Siwei Wang, Pei Zhang, Kai Xu, Xinwang Liu, Changwang Zhang, and Feng Gao. 2022. Efficient one-pass multi-view subspace clustering with consensus anchors. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 7576--7584.Google ScholarCross Ref
- Xinwang Liu. 2021. Incomplete multiple kernel alignment maximization for clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google ScholarDigital Library
- Xinwang Liu. 2022. Simplemkkm: Simple multiple kernel k-means. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).Google Scholar
- Xinwang Liu, Miaomiao Li, Chang Tang, Jingyuan Xia, Jian Xiong, Li Liu, Marius Kloft, and En Zhu. 2020. Efficient and effective regularized incomplete multi-view clustering. IEEE transactions on pattern analysis and machine intelligence 43, 8 (2020), 2634--2646.Google ScholarCross Ref
- Xinwang Liu, Li Liu, Qing Liao, Siwei Wang, Yi Zhang, Wenxuan Tu, Chang Tang, Jiyuan Liu, and En Zhu. 2021. One pass late fusion multi-view clustering. In International Conference on Machine Learning. PMLR, 6850--6859.Google Scholar
- Yue Liu, Ke Liang, Jun Xia, Sihang Zhou, Xihong Yang, Xinwang Liu, and Z. Stan Li. 2023. Dink-Net: Neural Clustering on Large Graphs. In Proc. of ICML.Google Scholar
- Yue Liu, Wenxuan Tu, Sihang Zhou, Xinwang Liu, Linxuan Song, Xihong Yang, and En Zhu. 2022. Deep Graph Clustering via Dual Correlation Reduction. In AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- Yue Liu, Xihong Yang, Sihang Zhou, Xinwang Liu, Siwei Wang, Ke Liang, Wenxuan Tu, and Liang Li. 2023. Simple contrastive graph clustering. IEEE Transactions on Neural Networks and Learning Systems (2023).Google ScholarCross Ref
- Yue Liu, Xihong Yang, Sihang Zhou, Xinwang Liu, Zhen Wang, Ke Liang, Wenxuan Tu, Liang Li, Jingcan Duan, and Cancan Chen. 2023. Hard sample aware network for contrastive deep graph clustering. In Proceedings of the AAAI conference on artificial intelligence, Vol. 37. 8914--8922.Google ScholarDigital Library
- Yue Liu, Sihang Zhou, Xinwang Liu, Wenxuan Tu, and Xihong Yang. 2022. Improved Dual Correlation Reduction Network. arXiv preprint arXiv:2202.12533 (2022).Google Scholar
- Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018).Google Scholar
- Xi Peng, Zhenyu Huang, Jiancheng Lv, Hongyuan Zhu, and Joey Tianyi Zhou. 2019. COMIC: Multi-view clustering without parameter selection. In International conference on machine learning. PMLR, 5092--5101.Google Scholar
- Jingkuan Song, Hanwang Zhang, Xiangpeng Li, Lianli Gao, Meng Wang, and Richang Hong. 2018. Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Transactions on Image Processing 27, 7 (2018), 3210--3221.Google ScholarCross Ref
- Yuan Sun, Dezhong Peng, Haixiao Huang, and Zhenwen Ren. 2022. Feature and semantic views consensus hashing for image set classification. In Proceedings of the 30th ACM International conference on multimedia. 2097--2105.Google ScholarDigital Library
- Yuan Sun, Zhenwen Ren, Peng Hu, Dezhong Peng, and Xu Wang. 2023. Hierarchical Consensus Hashing for Cross-Modal Retrieval. IEEE Transactions on Multimedia (2023), 1--14. https://doi.org/10.1109/TMM.2023.3272169Google ScholarDigital Library
- Yuan Sun, Xu Wang, Dezhong Peng, Zhenwen Ren, and Xiaobo Shen. 2023. Hierarchical hashing learning for image set classification. IEEE Transactions on Image Processing 32 (2023), 1732--1744.Google ScholarDigital Library
- Cheng Tan, Zhangyang Gao, and Stan Z Li. 2022. SimVP: Towards Simple yet Powerful Spatiotemporal Predictive Learning. arXiv preprint arXiv:2211.12509 (2022).Google Scholar
- Cheng Tan, Zhangyang Gao, Lirong Wu, Siyuan Li, and Stan Z Li. 2022. Hyperspherical Consistency Regularization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7244--7255.Google ScholarCross Ref
- Cheng Tan, Siyuan Li, Zhangyang Gao, Wenfei Guan, Zedong Wang, Zicheng Liu, Lirong Wu, and Stan Z Li. 2023. OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning. arXiv preprint arXiv:2306.11249 (2023).Google Scholar
- Cheng Tan, Jun Xia, Lirong Wu, and Stan Z Li. 2021. Co-learning: Learning from noisy labels with self-supervision. In Proceedings of the 29th ACM International Conference on Multimedia. 1405--1413.Google ScholarDigital Library
- Chang Tang, Xinwang Liu, Xinzhong Zhu, En Zhu, Zhigang Luo, Lizhe Wang, and Wen Gao. 2020. CGD: Multi-view clustering via cross-view graph diffusion. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 5924--5931.Google ScholarCross Ref
- Huayi Tang and Yong Liu. 2022. Deep Safe Multi-view Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 202--211.Google ScholarCross Ref
- Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2020. Contrastive multiview coding. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XI 16. Springer, 776--794.Google ScholarDigital Library
- 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
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).Google Scholar
- Xinhang Wan, Jiyuan Liu, Weixuan Liang, Xinwang Liu, Yi Wen, and En Zhu. 2022. Continual multi-view clustering. In Proceedings of the 30th ACM International Conference on Multimedia. 3676--3684.Google ScholarDigital Library
- Xinhang Wan, Jiyuan Liu, Jue Wang, Xinwang Liu, Siwei Wang, Yi Wen, Tianjiao Wan, and En Zhu. 2023. One-step Multi-view Clustering with Diverse Representation. arXiv preprint arXiv:2306.05437 (2023).Google Scholar
- Xinhang Wan, Xinwang Liu, Jiyuan Liu, Siwei Wang, Yi Wen, Weixuan Liang, En Zhu, Zhe Liu, and Lu Zhou. 2023. Auto-weighted multi-view clustering for large-scale data. arXiv preprint arXiv:2303.01983 (2023).Google Scholar
- Xinhang Wan, Bin Xiao, Xinwang Liu, Jiyuan Liu, Weixuan Liang, and En Zhu. 2023. Fast Continual Multi-View Clustering with Incomplete Views. arXiv preprint arXiv:2306.02389 (2023).Google Scholar
- Siwei Wang, Xinwang Liu, Li Liu, Sihang Zhou, and En Zhu. 2021. Late fusion multiple kernel clustering with proxy graph refinement. IEEE Transactions on Neural Networks and Learning Systems (2021).Google ScholarCross Ref
- Siwei Wang, Xinwang Liu, Suyuan Liu, Jiaqi Jin, Wenxuan Tu, Xinzhong Zhu, and En Zhu. 2022. Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences. Advances in Neural Information Processing Systems 35 (2022), 5882--5895.Google Scholar
- SiweiWang, Xinwang Liu, Xinzhong Zhu, Pei Zhang, Yi Zhang, Feng Gao, and En Zhu. 2021. Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance. IEEE Transactions on Image Processing 31 (2021), 556--568.Google Scholar
- Jie Wen, Zheng Zhang, Yong Xu, and Zuofeng Zhong. 2018. Incomplete multiview clustering via graph regularized matrix factorization. In Proceedings of the European conference on computer vision (ECCV) workshops. 0-0.Google Scholar
- Yi Wen, Siwei Wang, Qing Liao, Weixuan Liang, Ke Liang, Xinhang Wan, and Xinwang Liu. 2023. Unpaired Multi-View Graph Clustering with Cross-View Structure Matching. arXiv preprint arXiv:2307.03476 (2023).Google Scholar
- Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, and Zenglin Xu. 2021. Deep embedded multi-view clustering with collaborative training. Information Sciences 573 (2021), 279--290.Google ScholarCross Ref
- Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, and Zenglin Xu. 2021. Deep embedded multi-view clustering with collaborative training. Information Sciences 573 (2021), 279--290.Google ScholarCross Ref
- Jie Xu, Yazhou Ren, Huayi Tang, Xiaorong Pu, Xiaofeng Zhu, Ming Zeng, and Lifang He. 2021. Multi-VAE: Learning disentangled view-common and viewpeculiar visual representations for multi-view clustering. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9234--9243.Google ScholarCross Ref
- Jie Xu, Yazhou Ren, Huayi Tang, Zhimeng Yang, Lili Pan, Yang Yang, Xiaorong Pu, S Yu Philip, and Lifang He. 2022. Self-supervised discriminative feature learning for deep multi-view clustering. IEEE Transactions on Knowledge and Data Engineering (2022).Google ScholarDigital Library
- Jie Xu, Yazhou Ren, Huayi Tang, Zhimeng Yang, Lili Pan, Yang Yang, Xiaorong Pu, S Yu Philip, and Lifang He. 2022. Self-supervised discriminative feature learning for deep multi-view clustering. IEEE Transactions on Knowledge and Data Engineering (2022).Google ScholarDigital Library
- Jie Xu, Huayi Tang, Yazhou Ren, Liang Peng, Xiaofeng Zhu, and Lifang He. 2022. Multi-level feature learning for contrastive multi-view clustering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16051-- 16060.Google ScholarCross Ref
- Xihong Yang, Xiaochang Hu, Sihang Zhou, Xinwang Liu, and En Zhu. 2022. Interpolation-Based Contrastive Learning for Few-Label Semi-Supervised Learning. IEEE Transactions on Neural Networks and Learning Systems (2022), 1--12. https://doi.org/10.1109/TNNLS.2022.3186512Google ScholarCross Ref
- Xihong Yang, Yue Liu, Sihang Zhou, Xinwang Liu, and En Zhu. 2022. Mixed Graph Contrastive Network for Semi-Supervised Node Classification. arXiv preprint arXiv:2206.02796 (2022).Google Scholar
- Xihong Yang, Yue Liu, Sihang Zhou, Siwei Wang, Xinwang Liu, and En Zhu. 2022. Contrastive Deep Graph Clustering with Learnable Augmentation. arXiv preprint arXiv:2212.03559 (2022).Google Scholar
- Xihong Yang, Yue Liu, Sihang Zhou, Siwei Wang, Wenxuan Tu, Qun Zheng, Xinwang Liu, Liming Fang, and En Zhu. 2023. Cluster-guided Contrastive Graph Clustering Network. In Proceedings of the AAAI conference on artificial intelligence, Vol. 37. 10834--10842.Google ScholarDigital Library
- Changqing Zhang, Yeqing Liu, and Huazhu Fu. 2019. Ae2-nets: Autoencoder in autoencoder networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2577--2585.Google ScholarCross Ref
- Pei Zhang, Siwei Wang, Jingtao Hu, Zhen Cheng, Xifeng Guo, En Zhu, and Zhiping Cai. 2020. Adaptive weighted graph fusion incomplete multi-view subspace clustering. Sensors 20, 20 (2020), 5755.Google ScholarCross Ref
- Handong Zhao, Zhengming Ding, and Yun Fu. 2017. Multi-view clustering via deep matrix factorization. In Proceedings of the AAAI conference on artificial intelligence, Vol. 31.Google ScholarCross Ref
- Runwu Zhou and Yi-Dong Shen. 2020. End-to-end adversarial-attention network for multi-modal clustering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 14619--14628.Google ScholarCross Ref
- Runwu Zhou and Yi-Dong Shen. 2020. End-to-end adversarial-attention network for multi-modal clustering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 14619--14628.Google ScholarCross Ref
- Sihang Zhou, Xinwang Liu, Miaomiao Li, En Zhu, Li Liu, Changwang Zhang, and Jianping Yin. 2019. Multiple kernel clustering with neighbor-kernel subspace segmentation. IEEE transactions on neural networks and learning systems 31, 4 (2019), 1351--1362.Google ScholarCross Ref
- Sihang Zhou, En Zhu, Xinwang Liu, Tianming Zheng, Qiang Liu, Jingyuan Xia, and Jianping Yin. 2020. Subspace segmentation-based robust multiple kernel clustering. Information Fusion 53 (2020), 145--154.Google ScholarDigital Library
- Pengfei Zhu, Binyuan Hui, Changqing Zhang, Dawei Du, Longyin Wen, and Qinghua Hu. 2019. Multi-view deep subspace clustering networks. arXiv preprint arXiv:1908.01978 (2019).Google Scholar
Index Terms
- DealMVC: Dual Contrastive Calibration for Multi-view Clustering
Recommendations
Contrastive and attentive graph learning for multi-view clustering
AbstractGraph-based multi-view clustering aims to take advantage of multiple view graph information to provide clustering solutions. The consistency constraint of multiple views is the key of multi-view graph clustering. Most existing studies ...
Highlights- A novel CAGL framework for multi-view clustering is proposed.
- CL is used to ...
Multi-view clustering via spectral partitioning and local refinement
A new multi-view clustering algorithm is proposed.The proposed MVNC algorithm uses spectral partitioning and local refinement.MVNC is compared to state-of-the-art algorithms using three real-world datasets.MVNC significantly outperforms the other ...
Multi-view clustering with dual tensors
AbstractMulti-view clustering methods based on tensor have achieved favorable performance thanks to the powerful capacity of capturing the high-order correlation hidden in multi-view data. However, many existing works only pay attention to exploring the ...
Comments