{"type":"ScholarlyArticle","title":"Self-supervised Weighted Information Bottleneck for Multi-view Clustering","authors":[{"name":"Zhengzheng Lou","slug":"zhengzheng-lou","given":"Zhengzheng","family":"Lou","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"},{"name":"Chaoyang Zhang","slug":"chaoyang-zhang","given":"Chaoyang","family":"Zhang","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"},{"name":"Hang Xue","slug":"hang-xue","given":"Hang","family":"Xue","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"},{"name":"Yangdong Ye","slug":"yangdong-ye","given":"Yangdong","family":"Ye","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"},{"name":"Qinglei Zhou","slug":"qinglei-zhou","given":"Qinglei","family":"Zhou","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"},{"name":"Shizhe Hu","slug":"shizhe-hu","given":"Shizhe","family":"Hu","affiliation":"School of Computer and Artificial Intelligence , Zhengzhou University , China"}],"abstract":"Multi-view clustering (MVC) is a long-standing topic in machine learning and data mining community, focusing on investigating and utilizing the relationships among views for final consistent data cluster structure discovery. Generally, weighted MVC is one of the popular methods working by learning and applying the view weight/importance on each view for fully exploring the complementary information across views. However, most existing weighted MVCs only consider the quality of each view, ignoring the vital role of pseudo label self-supervision information in weight learning. In this work, we propose a novel self-supervised weighted information bottleneck (SWIB) method for solving the multi-view clustering problem. It combines the weighted information from different views based on information bottleneck theory, and the view weight learning mechanism is newly designed by simultaneously taking into accounting both the quality of view-contained information and the self-supervised information on the data partition of each view. Experimental results on multi-view text, multi-feature image, multi-angle video, and multi-modal text-image dataset as well as large-scale datasets show the superiority of the SWIB method. To our knowledge, this is the first work incorporating the self-supervised learning into weighted multi-view clustering.","doi":"10.24963/ijcai.2024/513","url":"https://ijcai.org/proceedings/2024/513","pdf":"https://ijcai.org/proceedings/2024/0513.pdf","markdown":"https://ijcai.org/proceedings/2024/513.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/513","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":513,"pages":{"first":4643,"last":4650},"keywords":["Machine Learning: ML: Clustering","Machine Learning: ML: Multi-modal learning","Machine Learning: ML: Unsupervised learning","Machine Learning: ML: Multi-view learning"],"videos":[],"references":[{"position":1,"raw":"[Bardera et al., 2009] Anton Bardera, Jaume Rigau, Imma Boada, Miquel Feixas, and Mateu Sbert. Image segmen- tation using information bottleneck method. IEEE Trans. Image Process., 18(7):1601-1612, 2009.","title":"Image segmentation using information bottleneck method","authors":"Bardera","year":"2009","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bickel and Scheffer, 2004] Steffen Bickel and Tobias Scheffer. Multi-view clustering. In Proceedings of the 4th IEEE International Conference on Data Mining (ICDM), pages 19-26, 2004.","title":"Multi-view clustering","authors":"Scheffer Bickel, Steffen Bickel, Tobias Scheffer","year":"2004","venue":"Proceedings of the 4th IEEE International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai et al., 2013] Xiao Cai, Feiping Nie, and Heng Huang. Multi-view k-means clustering on big data. In Proceed- ings of the 23rd International Joint Conference on Artifi- cial Intelligence, pages 2598-2604, 2013.","title":"Multi-view k-means clustering on big data","authors":"Xiao Cai, Feiping Nie, Heng Huang","year":"2013","venue":"Proceed-ings of the 23rd International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2013/383"},{"position":4,"raw":"[Chen et al., 2022] Mansheng Chen, Chang-Dong Wang, Dong Huang, Jian-Huang Lai, and Philip S. Yu. Efficient orthogonal multi-view subspace clustering. In The 28th ACM SIGKDD, pages 127-135, 2022.","title":"Efficient orthogonal multi-view subspace clustering","authors":"Mansheng Chen, Chang-Dong Wang, Dong Huang, Jian-Huang Lai, Philip S Yu","year":"2022","venue":"The 28th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cover and Thomas, 2006] Thomas M. Cover and Joy A. Thomas. Elements of Information Theory. Wiley- Interscience, 2006.","title":"Elements of Information Theory","authors":"Thomas M Cover, Joy A Thomas","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cui et al., 2023] Chenhang Cui, Yazhou Ren, Jingyu Pu, Xiaorong Pu, and Lifang He. Deep multi-view subspace clustering with anchor graph. In Proceedings of the Thirty- Second International Joint Conference on Artificial Intel- ligence, IJCAI, pages 3577-3585, 2023.","title":"Deep multi-view subspace clustering with anchor graph","authors":"Cui","year":"2023","venue":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/398"},{"position":7,"raw":"[Fei-Fei and Perona, 2005] Li Fei-Fei and Pietro Perona. A bayesian hierarchical model for learning natural scene cat- egories. In IEEE CVPR, pages 524-531, 2005.","title":"A bayesian hierarchical model for learning natural scene categories","authors":"Fei-Fei, Perona, Li Fei-Fei, Pietro Perona","year":"2005","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2007] Yan Gao, Shiwen Gu, Jianhua Li, and Zhining Liao. The multi-view information bottleneck clus- tering. In 12th International Conference on Database Sys- tems for Advanced Applications, DASFAA, volume 4443, pages 912-917, 2007.","title":"The multi-view information bottleneck clustering","authors":"Yan Gao, Shiwen Gu, Jianhua Li, Zhining Liao","year":"2007","venue":"12th International Conference on Database Systems for Advanced Applications, DASFAA","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2021] Shizhe Hu, Xiaoqiang Yan, and Yangdong Ye. Multi-task image clustering through correlation propa- gation. IEEE Trans. Knowl. Data Eng., 33(3):1113-1127, 2021.","title":"Multi-task image clustering through correlation propagation","authors":"Hu","year":"2021","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hu et al., 2022a] Shizhe Hu, Zhengzheng Lou, and Yang- dong Ye. View-wise versus cluster-wise weight: Which is better for multi-view clustering? IEEE Trans. Image Process., 31:58-71, 2022.","title":"View-wise versus cluster-wise weight: Which is better for multi-view clustering?","authors":"Hu","year":"2022","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hu et al., 2022b] Shizhe Hu, Zenglin Shi, and Yangdong Ye. DMIB: dual-correlated multivariate information bot- tleneck for multiview clustering. IEEE Trans. Cybern., 52(6):4260-4274, 2022.","title":"DMIB: dual-correlated multivariate information bottleneck for multiview clustering","authors":"Hu","year":"2022","venue":"IEEE Trans. Cybern","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hu et al., 2024] Shizhe Hu, Zhengzheng Lou, Xiaoqiang Yan, and Yangdong Ye. A survey on information bottle- neck. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), pages 1-20, 2024.","title":"A survey on information bottleneck","authors":"Hu","year":"2024","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Huang et al., 2023] Zongmo Huang, Yazhou Ren, Xiaorong Pu, Shudong Huang, Zenglin Xu, and Lifang He. Self- supervised graph attention networks for deep weighted multi-view clustering. In Thirty-Seventh AAAI Conference on Artificial Intelligence, pages 7936-7943, 2023.","title":"Selfsupervised graph attention networks for deep weighted multi-view clustering","authors":"Huang","year":"2023","venue":"Thirty-Seventh AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Khan et al., 2009] Fahad Shahbaz Khan, Joost van de Wei- jer, and María Vanrell. Top-down color attention for object recognition. In Proc. ICCV, pages 979-986, 2009.","title":"Top-down color attention for object recognition","authors":"Fahad Shahbaz Khan, Joost Van De Weijer, María Vanrell","year":"2009","venue":"Proc. ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Laptev, 2005] Ivan Laptev. On space-time interest points. Int. J. Comput. Vis., 64(2-3):107-123, 2005.","title":"On space-time interest points","authors":"Ivan Laptev, Laptev","year":"2005","venue":"Int. J. Comput. Vis","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lou et al., 2013] Zhengzheng Lou, Yangdong Ye, and Xi- aoqiang Yan. The multi-feature information bottleneck with application to unsupervised image categorization. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence, pages 1508-1515, 2013.","title":"Zhengzheng Lou, Yangdong Ye, and Xiaoqiang Yan. The multi-feature information bottleneck with application to unsupervised image categorization","authors":"Lou","year":"2013","venue":"Proceedings of the 23rd International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lowe, 2004] David G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91-110, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"G David, Lowe","year":"2004","venue":"Int. J. Comput. Vis","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nie et al., 2018] Feiping Nie, Guohao Cai, Jing Li, and Xuelong Li. Auto-weighted multi-view learning for im- age clustering and semi-supervised classification. IEEE Trans. Image Process., 27(3):1501-1511, 2018.","title":"Auto-weighted multi-view learning for image clustering and semi-supervised classification","authors":"Nie","year":"2018","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sun et al., 2021] Mengjing Sun, Pei Zhang, Siwei Wang, Sihang Zhou, Wenxuan Tu, Xinwang Liu, En Zhu, and Changjian Wang. Scalable multi-view subspace cluster- ing with unified anchors. In ACM Multimedia Conference, pages 3528-3536, 2021.","title":"Scalable multi-view subspace clustering with unified anchors","authors":"Mengjing Sun, Pei Zhang, Siwei Wang, Sihang Zhou, Wenxuan Tu, Xinwang Liu, En Zhu, Changjian Wang","year":"2021","venue":"ACM Multimedia Conference","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tishby et al., 1999] Naftali Tishby, Fernando C Pereira, and William Bialek. The information bottleneck method. In Proc. Annual Allerton Conf. Communnication Control Computing, pages 368-377, 1999.","title":"The information bottleneck method","authors":"Naftali Tishby, Fernando C Pereira, William Bialek","year":"1999","venue":"Proc. Annual Allerton Conf. Communnication Control Computing","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2020] Hao Wang, Yan Yang, and Bing Liu. GMC: graph-based multi-view clustering. IEEE Trans. Knowl. Data Eng., 32(6):1116-1129, 2020.","title":"GMC: graph-based multi-view clustering","authors":"Hao Wang, Yan Yang, Bing Liu","year":"2020","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2022] Siwei Wang, Xinwang Liu, Xinzhong Zhu, Pei Zhang, Yi Zhang, Feng Gao, and En Zhu. Fast parameter-free multi-view subspace clustering with con- sensus anchor guidance. IEEE Trans. Image Process., 31:556-568, 2022.","title":"Fast parameter-free multi-view subspace clustering with consensus anchor guidance","authors":"Siwei Wang, Xinwang Liu, Xinzhong Zhu, Pei Zhang, Yi Zhang, Feng Gao, En Zhu","year":"2022","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wen et al., 2021] Jie Wen, Zheng Zhang, Zhao Zhang, Lunke Fei, and Meng Wang. Generalized incomplete mul- tiview clustering with flexible locality structure diffusion. IEEE Trans. Cybern., 51(1):101-114, 2021.","title":"Generalized incomplete multiview clustering with flexible locality structure diffusion","authors":"Jie Wen, Zheng Zhang, Zhao Zhang, Lunke Fei, Meng Wang","year":"2021","venue":"IEEE Trans. Cybern","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wen et al., 2023] Jie Wen, Chengliang Liu, Gehui Xu, Zhi- hao Wu, Chao Huang, Lunke Fei, and Yong Xu. Highly confident local structure based consensus graph learning for incomplete multi-view clustering. In CVPR, pages 15712-15721, 2023.","title":"Highly confident local structure based consensus graph learning for incomplete multi-view clustering","authors":"Jie Wen, Chengliang Liu, Gehui Xu, Zhihao Wu, Chao Huang, Lunke Fei, Yong Xu","year":"2023","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wolf et al., 2008] Lior Wolf, Tal Hassner, and Yaniv Taig- man. Descriptor based methods in the wild. In Real-Life Images workshop at ECCV, 2008.","title":"Descriptor based methods in the wild","authors":"Lior Wolf, Tal Hassner, Yaniv Taigman","year":"2008","venue":"Real-Life Images workshop at ECCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xia et al., 2023] Wei Xia, Quanxue Gao, Qianqian Wang, Xinbo Gao, Chris Ding, and Dacheng Tao. Tensorized bipartite graph learning for multi-view clustering. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 45(4):5187-5202, 2023.","title":"Tensorized bipartite graph learning for multi-view clustering","authors":"Wei Xia, Quanxue Gao, Qianqian Wang, Xinbo Gao, Chris Ding, Dacheng Tao","year":"2023","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xu et al., 2016] Jinglin Xu, Junwei Han, and Feiping Nie. Discriminatively embedded k-means for multi-view clus- tering. In IEEE Conference on Computer Vision and Pat- tern Recognition, CVPR, pages 5356-5364, 2016.","title":"Discriminatively embedded k-means for multi-view clustering","authors":"Jinglin Xu, Junwei Han, Feiping Nie","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2024] Cai Xu, Jiajun Si, Ziyu Guan, Wei Zhao, Yue Wu, and Xiyue Gao. Reliable conflictive multi-view learning. In AAAI, pages 16129-16137, 2024.","title":"Reliable conflictive multi-view learning","authors":"Cai Xu, Jiajun Si, Ziyu Guan, Wei Zhao, Yue Wu, Xiyue Gao","year":"2024","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2023] Chaoyang Zhang, Zhengzheng Lou, Qinglei Zhou, and Shizhe Hu. Multi-view clustering via triplex information maximization. IEEE Trans. Image Pro- cess., 32:4299-4313, 2023.","title":"Multi-view clustering via triplex information maximization","authors":"Zhang","year":"2023","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}