Multi-Label Learning With Label Specific Features Using Correlation Information

Han, Huirui; Huang, Mengxing; Yang, Xiaogang; Feng, Wenlong

doi:10.1109/access.2019.2891611

Cited by 44 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the second-order methods incorporate the classification criteria ranking loss into the objective function of multi-label learning, such as Rank-SVM [23], MIMLfast [24], and LSEP [25]. Second, the second-order methods constrain the label correlations to the model coefficients or outputs, such as [11,[35][36][37][38]. LLSF [35] used the correlation between the labels to learn specific label features for multi-label learning.…”

Section: Related Workmentioning

confidence: 99%

“…LLSF [35] used the correlation between the labels to learn specific label features for multi-label learning. LSF-CI [36] is a multi-label feature multilabel learning method which considered the relevant information of the label space and the feature space simultaneously. There are also some algorithms that tend to investigate global and local label correlations.…”

Section: Related Workmentioning

confidence: 99%

“…, w q ] ∈ R d×q , λ 1 and λ 2 are non-negative weight parameters. The Previous studies mainly constrain the correlation between labels on the model coefficient matrix or the output by manifold regularization [35,36]. Different from previous studies, we directly model the pairwise label correlations by graph embedding, and the structure of label correlation will be well kept in W.…”

Section: Label Correlation Embeddingmentioning

confidence: 99%

See 2 more Smart Citations

Improving Multi-Label Learning by Correlation Embedding

Huang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

In multi-label learning, each object is represented by a single instance and is associated with more than one class labels, where the labels might be correlated with each other. As we all know, exploiting label correlations can definitely improve the performance of a multi-label classification model. Existing methods mainly model label correlations in an indirect way, i.e., adding extra constraints on the coefficients or outputs of a model based on a pre-learned label correlation graph. Meanwhile, the high dimension of the feature space also poses great challenges to multi-label learning, such as high time and memory costs. To solve the above mentioned issues, in this paper, we propose a new approach for Multi-Label Learning by Correlation Embedding, namely MLLCE, where the feature space dimension reduction and the multi-label classification are integrated into a unified framework. Specifically, we project the original high-dimensional feature space to a low-dimensional latent space by a mapping matrix. To model label correlation, we learn an embedding matrix from the pre-defined label correlation graph by graph embedding. Then, we construct a multi-label classifier from the low-dimensional latent feature space to the label space, where the embedding matrix is utilized as the model coefficients. Finally, we extend the proposed method MLLCE to the nonlinear version, i.e., NL-MLLCE. The comparison experiment with the state-of-the-art approaches shows that the proposed method MLLCE has a competitive performance in multi-label learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Label Correlation Embeddingmentioning

confidence: 99%

See 1 more Smart Citation

Improving Multi-Label Learning by Correlation Embedding

Huang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…where YD is label-density matrix, R represents the cosine distance matrix [26], [39], [40] of each label in the labeldensity-margin space, C is the penalty factor, α parameter controls the label correlation, and λ controls the sparsity.…”

Section: B Extreme Elastic Netmentioning

confidence: 99%

Joint Label-Density-Margin Space and Extreme Elastic Net for Label-Specific Features

et al. 2019

View full text Add to dashboard Cite

The label-specific features learning is a kind of framework for extracting the specific features of each label for classification. At present, the label-specific features algorithm is generally based on the original label space to find a particular feature set. This kind of extraction method for label-specific features has a general adaptation when the label density is balanced. However, in most multi-label data sets, the number of positive and negative labels varies greatly, and the label density is unbalanced. And there is an inherent correlation between each label. When extracting label-specific features, the method needs to consider issues such as imbalanced label density and label correlations. Based on this, a label-specific features learning method based on Joint Label-density-margin Space and Extreme Elastic Net (JLSE2N) is proposed in this paper. Firstly, to enlarge the margin between the positive and negative labels in the original label space, the positive and negative label density of the total example are calculated. And the information of unbalanced label density is integrated into the label space, thus forming a priori knowledge of the label-density-margin space. Subsequently, to quickly extract the label-specific features, the elastic net regularization extreme learning machine is used for the first time to obtain the label-specific features. The transformed label density space is used to calculate the cosine similarity and is added to the L 2 regularization term to consider the correlation between pairs of labels. The L 1 regularization term in the elastic net can generate the sparse weight matrix to extract the required label-specific features. We compare the proposed method with five well-known algorithms on 11 benchmark data sets. Experimental analysis shows that our proposed method is superior to the state-of-the-art algorithms for multi-label learning.

show abstract

“…As we know, multi-label data in reality always contains a large amount of attributes [7], [11], [37], [38], [41], [50], and some attributes may be irrelevant and/or redundant, which will severely interfere with the classification performance of multi-label classifier. Attribute reduction, as an important means for data pre-processing, can effectively solve the curse of dimensionality.…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Attribute Reduction Based on Variable Precision Fuzzy Neighborhood Rough Set

2020

View full text Add to dashboard Cite

Multi-label attribute reduction as a common dimensionality reduction technique has obtained widely research in recent years. Most existing multi-label attribute reduction methods adopt discretization to deal with mixed data and have strict requirements on the condition of sample classification. However, the process of discretization may lead to information loss, moreover, strict conditions will increase the possibility of a sample classified into a wrong class. Based on this, we construct a multi-label attribute reduction method based on variable precision fuzzy neighborhood rough set. The main motivation is that the variable precision fuzzy neighborhood rough set can process multiple types of data without discretization and tolerate noisy data. Specifically, we first use the parameterized fuzzy neighborhood granule to define the fuzzy decision and decision class of each sample under different labels. Then, the fuzzy decision and decision classes under different labels are fused into the entire multi-label learning space. Finally, a multilabel attribute reduction algorithm is designed according to the defined maximum attribute significance criterion. Our experiments are conducted on a series of multi-label datasets, and the experimental results verify that the proposed algorithm achieves better classification performance than other state-of-the-art comparison algorithms.INDEX TERMS Attribute reduction, multi-label learning, rough set model, fuzzy neighborhood, variable precision.

show abstract

Multi-Label Learning With Label Specific Features Using Correlation Information

Cited by 44 publications

References 34 publications

Improving Multi-Label Learning by Correlation Embedding

Improving Multi-Label Learning by Correlation Embedding

Joint Label-Density-Margin Space and Extreme Elastic Net for Label-Specific Features

Multi-Label Attribute Reduction Based on Variable Precision Fuzzy Neighborhood Rough Set

Contact Info

Product

Resources

About