From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering
Shengju Yu, Zhibin Dong, Siwei Wang, Suyuan Liu, Ke Liang, Xinwang Liu, Yue Liu, Yi Zhang
摘要
Current multi-view clustering (MVC) techniques generally focus only on the relationship between anchors and samples, while overlooking that between anchors. Moreover, due to the lack of data labels, the cluster order is inconsistent across views and accordingly anchors encounter misalignment, which will confuse the graph structure and disorganize cluster representation. Even worse, it typically brings variance during forming spectral embedding, degenerating the stability of clustering results. In response to these concerns, in the paper we propose a MVC approach named DTP-SF-BVF. Concretely, we explicitly exploit the geometric properties between anchors via self-expression learning skill, and utilize topology learning strategy to feed captured anchoranchor features into anchor-sample graph so as to explore the manifold structure hidden within samples more adequately. To reduce the misalignment risk, we introduce a permutation mechanism for each view to jointly rearrange anchors according to respective view characteristics. Besides not involving selecting the baseline view, it also can coordinate with anchors in the unified framework and thereby facilitate the learning of anchors. Further, rather than forming spectrum and then performing embedding partitioning, based on the criterion that samples and clusters should be hard assignment, we manage to construct the cluster labels directly from original samples using the binary strategy, not only preserving the data diversity but avoiding variance. Experiments on multiple publicly available datasets confirm the effectiveness of proposed DTP-SF-BVF method.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 3 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- Anti-Degradation Lifelong Multi-View Clustering 引用了 Large-Scale Multi-View Subspace Clustering in Linear Time
- Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering 引用了 Multi-View Clustering in Latent Embedding Space
- Multi-level Feature Learning for Contrastive Multi-view Clustering 引用了 Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering
- Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View Clustering 引用了 Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering
引用它的顶会 Paper3
- Anti-Degradation Lifelong Multi-View ClusteringXingfeng Li, Hao Pan, Honglin Yuan, Yuan Sun 等CVPR 2026
- Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View ClusteringZheming Xu, Aiyue Tang, Shidi Chen, Xuechao Zou 等ICML 2026
- A Consensus Anchor-guided Hypergraph Framework for Incomplete Multi-view ClusteringYipin Hu, Yanxi Liu, Fangxi Liu, Yanwei Yu 等ICML 2026
它引用的 Paper32
- Large-Scale Multi-View Subspace Clustering in Linear TimeZhao Kang, Wangtao Zhou, Zhitong Zhao, Junming Shao 等AAAI 2020 · 574 次引用
- Multi-level Feature Learning for Contrastive Multi-view ClusteringJie Xu, Huayi Tang, Yazhou Ren, Liang Peng 等CVPR 2022 · 335 次引用
- Multi-View Clustering in Latent Embedding SpaceMan-Sheng Chen, Ling Huang, Chang-Dong Wang, Dong HuangAAAI 2020 · 275 次引用
- Cluster-Guided Contrastive Graph Clustering NetworkXihong Yang, Yue Liu, Sihang Zhou, Siwei Wang 等AAAI 2023 · 169 次引用
- Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view ClusteringJie Xu, Yazhou Ren, Huayi Tang, Xiaorong Pu 等ICCV 2021 · 158 次引用
相关 Paper
- Learning Anchor in Dual Orthogonal Space for Fast Multi-view ClusteringYalan Qin, Hanzhou WuCVPR 2026
- Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete ScenariosShengju Yu, Pei Zhang, Siwei Wang, Suyuan Liu 等NeurIPS 2025
- Anchor Learning with Potential Cluster Constraints for Multi-view ClusteringYawei Chen, Huibing Wang, Jinjia Peng, Yang WangAAAI 2025 · 13 次引用
- Scalable Incomplete Multi-View Clustering with Structure AlignmentYi Wen, Siwei Wang, Ke Liang, Weixuan Liang 等ACM MM 2023 · 36 次引用
- Multi-view Graph Clustering via Efficient Global-Local Spectral Embedding FusionPenglei Wang, Danyang Wu, Rong Wang, Feiping NieACM MM 2023 · 19 次引用
