Discriminative Nonnegative Matrix Factorization for dimensionality reduction

Babaee, Mohammadreza; Tsoukalas, Stefanos; Rigoll, Gerhard; Datcu, Mihai

doi:10.1016/j.neucom.2014.12.124

Cited by 71 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to demonstrate that our AGDNMF method improves the clustering performance, we compare it with the following algorithm, such as other K-means clustering method [35], PCA [9], non-negative matrix factorization NMF [10], graph regularized nonnegative matrix factorization (GNMF) [34], constrained nonnegative matrix factorization (CNMF) [28], robust graph regularized nonnegative matrix factorization (RGNMF) [36], discriminative nonnegative matrix factorization (DNMF) [26].…”

Section: B Comparison Methodsmentioning

confidence: 99%

“…In recent years, some researchers put forward some new algorithms by adding additional constraints to NMF. By using the label information and the non-negative coefficient matrix to construct the regularization constraints, Babaee and Tsoukalas [26] propose discriminative NMF (DNMF). By adding sparse constraints to the decomposed base matrix, Li et al [27] proposed local nonnegative matrix factorization (LNMF).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Graph Regularization Discriminant Nonnegative Matrix Factorization for Data Representation

Zhang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Nonnegative matrix factorization, as a classical part-based representation method, has been widely used in pattern recognition, data mining and other fields. However, the traditional nonnegative matrix factorization directly factoring decomposes the original data, and the original data often contains a lot of redundancy and noise, which seriously affect the subsequent processing of the data. In this work, we propose an adaptive graph regularization discriminant nonnegative matrix factorization (AGDNMF) for image clustering. The AGDNMF algorithm makes full use of local structure information and a small amount of label information. In AGDNMF, the local structure information can be more accurate and the label information can prevent the points with the same label from being merged into one point. These two items are combined into the objective function of NMF. In addition, we provide the update rules for the corresponding optimization functions and prove its convergence. A large number of experiments on different data sets show that the proposed algorithm has good clustering performance.

show abstract

Section: B Comparison Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive Graph Regularization Discriminant Nonnegative Matrix Factorization for Data Representation

Zhang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [43], the authors proposed to incorporate sparseness property into NMF and extended it to learn more specific features. Several other work have also been proposed [28,29,30,31,32] to extend NMF to broader applications. Different from these methods, in this work we only constraints the coefficients to be non-negative but allow the basis matrix to be the sample matrix, in which the samples could contain negative elements.…”

Section: Non-negative Matrix Factorizationmentioning

confidence: 99%

“…This dense representation would be non-negative due to the homogeneity on these samples, reminiscent of non-negative matrix factorization (NMF) problem in machine learning community [25,27], which aims to approximate a data matrix via multiplication of two non-negative factorial matrices. Several NMF methods are proposed in the past few years [28,29,30,31,32], trying to get more accurate approximation. However, NMF cannot be directly utilized for pattern classification.…”

Section: Introductionmentioning

confidence: 99%

Sparse, collaborative, or nonnegative representation: Which helps pattern classification?

Zhang

et al. 2019

Pattern Recognition

121

View full text Add to dashboard Cite

The use of sparse representation (SR) and collaborative representation (CR) for pattern classification has been widely studied in tasks such as face recognition and object categorization. Despite the success of SR/CR based classifiers, it is still arguable whether it is the 1 -norm sparsity or the 2 -norm collaborative property that brings the success of SR/CR based classification. In this paper, we investigate the use of nonnegative representation (NR) for pattern classification, which is largely ignored by previous work. Our analyses reveal that NR can boost the representation power of homogeneous samples while limiting the representation power of heterogeneous samples, making the representation sparse and discriminative simultaneously and thus providing a more effective solution to representation based classification than SR/CR. Our experiments demonstrate that the proposed NR based classifier (NRC) outperforms previous representation based classifiers. With deep features as inputs, it also achieves state-of-the-art performance on various visual classification tasks.

show abstract

“…The concept of sparse coding has become very popular in many fields of engineering such as signal analysis and processing [1], clustering and classification [2,3,4], and face recognition [5]. The idea behind a sparse representation is to approximate a signal by a linear combination of a small set of elements from a so called over-complete dictionary.…”

Section: Introductionmentioning

confidence: 99%

Relative attribute guided dictionary learning

Babaee¹,

Wolf²,

Rigoll³

2016

2016 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

A discriminative dictionary learning algorithm is proposed to find sparse signal representations using relative attributes as the available semantic information. In contrast, existing (discriminative) dictionary learning approaches utilize binary label information to enhance the discriminative property of the signal reconstruction residual, the sparse coding vectors or both. Compared to binary attributes or labels, relative attributes contain richer semantic information where the data is annotated with the attributes' strength. In this paper we use the relative attributes of training data indirectly to learn a discriminative dictionary. Precisely, we incorporate a rank function for the attributes in the dictionary learning process. In order to assess the quality of the obtained signals, we apply k-means clustering algorithm to the obtained signals and measure the clustering performance. Experimental results conducted on three datasets confirm that the proposed approach outperforms the state-of-the-art label based dictionary learning algorithms.

show abstract

Discriminative Nonnegative Matrix Factorization for dimensionality reduction

Cited by 71 publications

References 17 publications

Adaptive Graph Regularization Discriminant Nonnegative Matrix Factorization for Data Representation

Adaptive Graph Regularization Discriminant Nonnegative Matrix Factorization for Data Representation

Sparse, collaborative, or nonnegative representation: Which helps pattern classification?

Relative attribute guided dictionary learning

Contact Info

Product

Resources

About