Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance

Wang, Siwei; Liu, Xinwang; Zhu, Xiaoyan; Zhang, Pei; Zhang, Yi; Gao, Feng; Zhu, En

doi:10.1109/tip.2021.3131941

Cited by 174 publications

(66 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• FPMVS-CAG [52]. Fast parameter-free multi-view subspace clustering with consensus anchor guidance (FPMVS-CAG) combines the anchor selection and the graph construction into a parameter-free manner, and learns an anchor-based subspace representation for the final clustering.…”

Section: Baseline Methods and Experimental Settingsmentioning

confidence: 99%

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

Cai¹,

Dong²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-view subspace clustering aims to discover the hidden subspace structures from multiple views for robust clustering, and has been attracting considerable attention in recent years. Despite significant progress, most of the previous multi-view subspace clustering algorithms are still faced with two limitations. First, they usually focus on the consistency (or commonness) of multiple views, yet often lack the ability to capture the cross-view inconsistencies in subspace representations. Second, many of them overlook the local structures of multiple views and cannot jointly leverage multiple local structures to enhance the subspace representation learning. To address these two limitations, in this paper, we propose a jointly smoothed multi-view subspace clustering (JSMC) approach. Specifically, we simultaneously incorporate the cross-view commonness and inconsistencies into the subspace representation learning. The viewconsensus grouping effect is presented to jointly exploit the local structures of multiple views to regularize the view-commonness representation, which is further associated with the low-rank constraint via the nuclear norm to strengthen its cluster structure. Thus the cross-view commonness and inconsistencies, the view-consensus grouping effect, and the low-rank representation are seamlessly incorporated into a unified objective function, upon which an alternating optimization algorithm is performed to achieve a robust subspace representation for clustering. Experimental results on a variety of real-world multi-view datasets have confirmed the superiority of the proposed approach.

show abstract

Section: Baseline Methods and Experimental Settingsmentioning

confidence: 99%

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

Cai¹,

Dong²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, since each anchor set on a view is learned independently of other views, the cross-view information is inherently neglected in the construction of each single-view graph, which may lead to a degraded capacity of multiview expressiveness. Despite the progress, these methods [16], [17], [18], [19] either jointly construct a single anchor set for all views [16], [18], [19] or separately construct a single anchor set for each view [17], which, however, neglect the possibilities hidden between single and all, and dwell in the single-stage fusion strategy without the ability to capture the view-wise relationships in multiple stages. Furthermore, the requirement of dataset-specific hyperparameter-tuning in many of them [16], [17], [18], [20] also poses a practical hurdle for their real-world applications.…”

Section: Late Fusionmentioning

confidence: 99%

“…In single-view clustering, it has proved to be an effective strategy to represent largescale data samples via a set of anchors (also known as landmarks or representatives) [14], [15], which can substantially facilitate the computation of the graph construction and partitioning for large-scale datasets. When it goes from single-view to multi-view, the anchor-based formulation still shows its promising ability [16], [17], [18], [19], but also faces a series of new challenges, ranging from multi-view anchor selection to multi-view information fusion. Typically, Li et al [16] selected a set of anchors by performing kmeans on the concatenated multi-view features.…”

Section: Introductionmentioning

confidence: 99%

“…With this unified anchor set, a bipartite graph is built between data samples and anchors on each view, and then multiple bipartite graphs are fused into a consensus graph for the final clustering [16]. Wang et al [19] exploited the self-expressive loss to learn a set of unified anchors and a bipartite graph for all views. However, considering the diverse characteristics of multiple views, a single set of unified anchors may not sufficiently capture the rich and complementary information of all views.…”

Section: Introductionmentioning

confidence: 99%

“…However, considering the diverse characteristics of multiple views, a single set of unified anchors may not sufficiently capture the rich and complementary information of all views. Different from the pursuit of a single anchor set for all views [16], [19], Kang et al [17] learned a set of anchors on each view, and then built a bipartite…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity

Dong¹,

Wang²,

Lai³

2022

Preprint

View full text Add to dashboard Cite

Despite significant progress, there remain three limitations to the previous multi-view clustering algorithms. First, they often suffer from high computational complexity, restricting their feasibility for large-scale datasets. Second, they typically fuse multi-view information via one-stage fusion, neglecting the possibilities in multi-stage fusions. Third, dataset-specific hyperparameter-tuning is frequently required, further undermining their practicability. In light of this, we propose a fast multi-view clustering via ensembles (FastMICE) approach. Particularly, the concept of random view groups is presented to capture the versatile view-wise relationships, through which the hybrid early-late fusion strategy is designed to enable efficient multi-stage fusions. With multiple views extended to many view groups, three levels of diversity (w.r.t. features, anchors, and neighbors, respectively) are jointly leveraged for constructing the view-sharing bipartite graphs in the early-stage fusion. Then, a set of diversified base clusterings for different view groups are obtained via fast graph partitioning, which are further formulated into a unified bipartite graph for final clustering in the late-stage fusion. Remarkably, FastMICE has almost linear time and space complexity, and is free of dataset-specific tuning. Experiments on twenty multi-view datasets demonstrate its advantages in scalability (for extremely large datasets), superiority (in clustering performance), and simplicity (to be applied) over the state-of-the-art.

show abstract

Multi-view Subspace Clustering with Joint Tensor Representation and Indicator Matrix Learning

Wang¹,

Zhang²,

Liu³

et al. 2022

Artificial Intelligence

View full text Add to dashboard Cite

Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance

Cited by 174 publications

References 46 publications

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity

Multi-view Subspace Clustering with Joint Tensor Representation and Indicator Matrix Learning

Contact Info

Product

Resources

About