Weighted Multi-view Clustering with Feature Selection

Xu, Yumeng; Wang, Chang‐Dong; Lai, Jianhuang

doi:10.1016/j.patcog.2015.12.007

Cited by 173 publications

(66 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the performance of our method RRMVFS with several related methods: Single, CAT, RFS [Nie, Huang, Cai et al (2011)], SSMVFS ], SMML ], DSML-FS [Gui, Rao, Sun et al (2014)], and WMCFS [Xu, Wang and Lai (2016)]. Single refers to using single-view features to find best performance for classification.…”

Section: Methodsmentioning

confidence: 99%

“…The exponential parameter ρ in WMCFS method is set to be 5 according to Xu et al [Xu, Wang and Lai (2016)]. The public available data sets, including images data set NUS-WIDE-OBJECT (NUS), handwritten numerals data set mfeat, and Internet pages data set Ads are employed in the experiments.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, the concatenated vectors are always high dimensional, which increases the chance of over-fitting. Noticing these limitations, some multi-view clustering methods [Xu, Wang and Lai (2016); Xu, Han, Nie et al (2017)] have been proposed to learn the corresponding distribution of different views. Inspired by the above work, we propose a robust re-weighted multi-view feature selection method (RRMVFS) without concatenation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Re-Weighted Multi-View Feature Selection

Xue¹,

NanWang²,

Niu³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In practical application, many objects are described by multi-view features because multiple views can provide a more informative representation than the single view. When dealing with the multi-view data, the high dimensionality is often an obstacle as it can bring the expensive time consumption and an increased chance of over-fitting. So how to identify the relevant views and features is an important issue. The matrix-based multi-view feature selection that can integrate multiple views to select relevant feature subset has aroused widely concern in recent years. The existing supervised multi-view feature selection methods usually concatenate all views into the long vectors to design the models. However, this concatenation has no physical meaning and indicates that different views play the similar roles for a specific task. In this paper, we propose a robust re-weighted multi-view feature selection method by constructing the penalty term based on the low-dimensional subspaces of each view through the least-absolute criterion. The proposed model can fully consider the complementary property of multiple views and the specificity of each view. It can not only induce robustness to mitigate the impacts of outliers, but also learn the corresponding weights adaptively for different views without any presetting parameter. In the process of optimization, the proposed model can be splitted to several small scale sub-problems. An iterative algorithm based on the iteratively re-weighted least squares is proposed to efficiently solve these sub-problems. Furthermore, the convergence of the iterative algorithm is theoretical analyzed. Extensive comparable experiments with several state-of-the-art feature selection methods verify the effectiveness of the proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Re-Weighted Multi-View Feature Selection

Xue¹,

NanWang²,

Niu³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…It is known that feature weights in one view are in the interval [0,1], so the more influence a feature is, the greater its weight should be. Feature-weighted techniques had been used for multi-view k-means clustering algorithms, such as simultaneous weighting on views and features (SWVF) [12] and weighted multi-view clustering with feature selection (WMCFS) [14]. Although these feature-weighted clustering algorithms may improve the performance of k-means for multi-view data, they do not consider feature reduction.…”

Section: Introductionmentioning

confidence: 99%

A Feature-Reduction Multi-View k-Means Clustering Algorithm

Yang¹,

Sinaga²

2019

IEEE Access

105

View full text Add to dashboard Cite

The k-means clustering algorithm is the oldest and most known method in cluster analysis. It has been widely studied with various extensions and applied in a variety of substantive areas. Since internet, social network, and big data grow rapidly, multi-view data become more important. For analyzing multi-view data, various multi-view k-means clustering algorithms have been studied. However, most of multi-view k-means clustering algorithms in the literature cannot give feature reduction during clustering procedures. In general, there often exist irrelevant feature components in multi-view data sets that may cause bad performance for these clustering algorithms. There also exists high feature dimension in multi-view data sets so it is necessary to consider reducing its dimension for clustering algorithms. In this paper, a learning mechanism for the multi-view k-means algorithm to automatically compute individual feature weight is constructed. It can reduce these irrelevant feature components in each view. A new multi-view k-means objective function is firstly proposed for constructing the learning mechanism for feature weights in multiview clustering. A schema for eliminating irrelevant feature(s) with small weight(s) is then considered for feature reduction. Therefore, a new type of multi-view k-means, called a feature-reduction multi-view k-means (FRMVK), is proposed. The computational complexity of FRMVK is also analyzed. Numerical and real data sets are used to compare FRMVK with other feature-weighted multi-view k-means algorithms. Experimental results and comparisons actually demonstrate the effectiveness and usefulness of the proposed FRMVK clustering algorithm. INDEX TERMS Clustering, k-means, multi-view k-means, feature-reduction learning, feature-reduction multi-view k-means (FRMVK).

show abstract

“…Next, a consensus function combines the ensemble into a consolidated solution or consensus partition, which has greater overall accuracy [39,21,19,54,56,42,10,18]. Given the ill-posed nature of clustering, the accuracy is typically measured by comparing the final solution with a known reference partition, which is generally based on the class labels associated with the data set [20,50,30,41,46]. Although this reference partition might not be the only valid structure for the data, many studies have tried to determine how ensembles should be built, and which characteristics they should have to obtain high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Diversity control for improving the analysis of consensus clustering

Pividori

Stegmayer

Milone

2016

Information Sciences

View full text Add to dashboard Cite

Consensus clustering has emerged as a powerful technique for obtaining better clustering results, where a set of data partitions (ensemble) are generated, which are then combined to obtain a consolidated solution (consensus partition) that outperforms all of the members of the input set. The diversity of ensemble partitions has been found to be a key aspect for obtaining good results, but the conclusions of previous studies are contradictory. Therefore,

show abstract

Weighted Multi-view Clustering with Feature Selection

Cited by 173 publications

References 21 publications

Robust Re-Weighted Multi-View Feature Selection

Robust Re-Weighted Multi-View Feature Selection

A Feature-Reduction Multi-View k-Means Clustering Algorithm

Diversity control for improving the analysis of consensus clustering

Contact Info

Product

Resources

About