Consensus Graph Learning for Multi-View Clustering

Li, Zhenglai; Tang, Chang; Liu, Xinwang; Zheng, Xiao; Yue, Guanghui; Zhang, Wei; Zhu, En

doi:10.1109/tmm.2021.3081930

Cited by 168 publications

(38 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a representative unsupervised multi-view learning method [29,6,8,42], multi-view graph clustering (MVGC) represents single-view structures with graphs and then operates graph fusion on individual graphs [17,32,25,3,47]. Many graph approaches have been proposed with the differences of these two parts.…”

Section: Multi-view Graph Clusteringmentioning

confidence: 99%

Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences

Wang¹,

Liu²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-view anchor graph clustering selects representative anchors to avoid full pairwise similarities and therefore reduce the complexity of graph methods. Although widely applied in large-scale applications, existing approaches do not pay sufficient attention to establishing correct correspondences between the anchor sets across views. To be specific, anchor graphs obtained from different views are not aligned column-wisely. Such an Anchor-Unaligned Problem (AUP) would cause inaccurate graph fusion and degrade the clustering performance. Under multi-view scenarios, generating correct correspondences could be extremely difficult since anchors are not consistent in feature dimensions. To solve this challenging issue, we propose the first study of a generalized and flexible anchor graph fusion framework termed Fast Multi-View Anchor-Correspondence Clustering (FMVACC). Specifically, we show how to find anchor correspondence with both feature and structure information, after which anchor graph fusion is performed column-wisely. Moreover, we theoretically show the connection between FMVACC and existing multi-view late fusion [19] and partial view-aligned clustering [7], which further demonstrates our generality. Extensive experiments on seven benchmark datasets demonstrate the effectiveness and efficiency of our proposed method. Moreover, the proposed alignment module also shows significant performance improvement applying to existing multi-view anchor graph competitors indicating the importance of anchor alignment.Preprint. Under review.

show abstract

Section: Multi-view Graph Clusteringmentioning

confidence: 99%

Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences

Wang¹,

Liu²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…e computational complexity of the three proposed algorithms is the same as each other because the first two steps are similar. e first step is to solve equation (15). It requires ncD i for computing (X (i) ) T Y (i) , and O(2cD 2 i + ncD i ) for forming W (i) .…”

Section: Computational Complexity Analysismentioning

confidence: 99%

“…is pattern is explainable since a higher value of λ will force MvLRFD to focus more on fused information between views. for each iv ∈ [1, n v ] do (5) Computer the basis of i-th view using ( 16); (6) Computer latent representation of v-th view using ( 19); (7) Update the Dive using Dive � Dive + HY (i) (Y (i) ) T H; (8) end for (9) Update weight vector α using ( 22); (10) Update S using ( 29); (11) Compute the value of the objective function J t using ( 13); (12) if (|J t − J| < 1e − 3)‖(iter > maxIter) then (13) break; ( 14) else (15) J⟵J t ; (16) end if (17) iter⟵iter + 1; (18) end for (19) return the final representation using (8); ALGORITHM 1: e algorithm of MvLRFD. With σ � 2 2 and λ � 2 2 , our method will obtain a better performance for maintaining private information when 2 − 2 ≥ β ≥ 2 − 4 .…”

Section: Parameter Sensitivity Analysis and Convergencementioning

confidence: 99%

“…For exploring the complementary information among multiview data, Cao et al proposed Diversity-induced Multiview Subspace Clustering (DiMSC) [13] which utilizes the Hilbert-Schmidt Independence Criterion (HSIC) as a diversity term to explore the complementary representations of multiview. Later, Tang et al proposed two different multiview subspace clustering methods [14,15]. Mi et al proposed diversity and consistency embedding learning [16] for multiview subspace clustering.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiview Latent Representation Learning with Feature Diversity for Clustering

Wang

Chen

Peng³

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

To analyze and manage data, multiple features are extracted for robust and accurate description. Taking account of the complementary nature of multiview data, it is urgent to find a low-dimensional compact representation by leveraging multiple views and generating a better performance for clustering. In this paper, we present multiview latent representation learning with feature diversity for clustering (MvLRFD). To get rid of noise and maintain the information of each view, matrix factorization is adopted to get the latent representation. For fusing the diverse latent representations, we argue that the final representation is constructed by concatenating the latent representation of each view. With the help of the Hilbert–Schmidt Independence Criterion (HSIC), the diversity of features in the final representation is maximized to exploit the complementary information. A new coregularization strategy is introduced to maximize the distance between the similarity between data of the final representation and the latent one. The partition entropy regularization is adopted to control the uniformity level of the value of the similarity matrix and the weight of each view. To verify the availability of MvLRFD compared to state-of-the-art algorithms, several experiments are conducted on four real datasets.

show abstract

“…represent richer semantic features of observation objects than single-view data [1]- [3]. In the area of data analysis, multiview clustering has aroused extensive research enthusiasm [4]- [7], and researchers have developed a large amount of multiview clustering methods in the last few years.…”

mentioning

confidence: 99%

Localized Sparse Incomplete Multi-view Clustering

Liu,

Wu,

Wen

et al. 2022

Preprint

View full text Add to dashboard Cite

Incomplete multi-view clustering, which aims to solve the clustering problem on the incomplete multi-view data with partial view missing, has received more and more attention in recent years. Although numerous methods have been developed, most of the methods either cannot flexibly handle the incomplete multi-view data with arbitrary missing views or do not consider the negative factor of information imbalance among views. Moreover, some methods do not fully explore the local structure of all incomplete views. To tackle these problems, this paper proposes a simple but effective method, named localized sparse incomplete multi-view clustering (LSIMVC). Different from the existing methods, LSIMVC intends to learn a sparse and structured consensus latent representation from the incomplete multi-view data by optimizing a sparse regularized and novel graph embedded multi-view matrix factorization model. Specifically, in such a novel model based on the matrix factorization, a l1 norm based sparse constraint is introduced to obtain the sparse low-dimensional individual representations and the sparse consensus representation. Moreover, a novel local graph embedding term is introduced to learn the structured consensus representation. Different from the existing works, our local graph embedding term aggregates the graph embedding task and consensus representation learning task into a concise term. Furthermore, to reduce the imbalance factor of incomplete multi-view learning, an adaptive weighted learning scheme is introduced to LSIMVC. Finally, an efficient optimization strategy is given to solve the optimization problem of our proposed model. Comprehensive experimental results performed on six incomplete multi-view databases verify that the performance of our LSIMVC is superior to the state-of-the-art IMC approaches. The code is available in https://github.com/justsmart/LSIMVC.

show abstract

Consensus Graph Learning for Multi-View Clustering

Cited by 168 publications

References 49 publications

Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences

Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences

Multiview Latent Representation Learning with Feature Diversity for Clustering

Localized Sparse Incomplete Multi-view Clustering

Contact Info

Product

Resources

About