Manifold regularized discriminative feature selection for multi-label learning

Jia, Zhang; Luo, Zhiming; Li, Candong; Zhou, Chunyan; Li, Shaozi

doi:10.1016/j.patcog.2019.06.003

Cited by 246 publications

(54 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seo et al [30] proposed an improved k-cardinality entropy approximationbased criterion of multi-label feature selection and investigated the parameter k. Sun et al [33] presented a mutual information based method which obtained the optimal subset of features via constrained convex optimization. Zhang et al [42] presented an algorithm called MDFS, which exploits label correlations via manifold regularization, then selects optimal features with l 1,2 −norm regularization and convexity. Li et al [17] put forward a multi-label feature section based on granular computing, which granulates label space firstly, then select the optimal feature subset with a multi-label maximal correlation and minimal redundancy criterion.…”

Section: A Multi-label Feature Selection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets

et al. 2020

View full text Add to dashboard Cite

Multi-label learning is often applied to handle complex decision tasks, and feature selection is its essential part. The relation of labels is always ignored or not enough to consider for both multi-label learning and its feature selection. To deal with the problem, F-neighborhood rough sets are employed. Different from other methods, the original approximate space is not changed, but the relation of labels is sufficient to consider. To be specific, a multi-label decision system is discomposed into a family of singlelabel decision tables with the label set(first-order strategy) at first. Secondly, calculate attribute significance in the family of single-label decision tables. Third, construct an attribute significance matrix and improved attribute significance matrices to evaluate the quality of the features, then a parallel reduct is obtained with information fusion. These processes construct F-neighborhood parallel reduction algorithm for a multi-label decision system(FNPRMS). Compared with the state-of-the-arts, experimental results show that FNPRMS is effective and efficient on 9 publicly available data sets.

show abstract

Section: A Multi-label Feature Selection Methodsmentioning

confidence: 99%

“…In order to verify the validity of FNPRMS and its feasibility, experiments are designed to compare with the other six multilabel feature selection algorithms, including MLNB [45], MDDMspc [44], MDDMproj [44], PMU [16], MLFRS [23] and MDFS [42]. the parameter smooth in MLNB is set up to 1, as recommended in [45].…”

Section: B Experiments Settingsmentioning

confidence: 99%

Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The method of manifold regularized discriminative feature selection 35 mapped the original feature information into a low-dimensional space for capturing the local label correlations, and then constructed the label information constrained by a manifold to explore the global correlations.…”

Section: Related Workmentioning

confidence: 99%

Joint multilabel classification and feature selection based on deep canonical correlation analysis

Dai

Zhang

et al. 2020

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

In recent years, multilabel learning has been applied to a lot of application areas and is yet a challenging task. In multilabel learning, an instance often belongs to multiple class labels simultaneously. The labels usually have correlations with others, and mining label correlations is helpful to enhance the multilabel classification performance. Aiming at increasing the accuracy of prediction, Label embedding (LE) is an important technique, and conducive to extracting label information for multilabel learning. In this paper, we present a novel multilabel learning approach via exploiting label correlations, which can be naturally extended to tackle feature selection problem. First, to obtain the discriminative features shared by all labels, the proposed algorithm learns a latent space by employing deep canonical correlation analysis. Then we exploit label correlations by enforcing predictions on similar labels to be similar, thereby improving the prediction performance. Results on several multiple datasets illustrate that the proposed algorithm has the advantages on multilabel classification and feature selection.

show abstract

“…All the predicted results will be compared with three traditional algorithms, namely KNN, DT, and SVM. Note that the evaluation metrics involved in the experiments include Hamming loss (HL), Coverage, Ranking loss (RL), Average precision (AVP), and the performance of multi-label algorithm can obtain the objective evaluation data by these metrics [21,22]. For AVP, the higher the average accuracy is, the better the model is, and for the others the smaller the evaluation indexes are, the better the model is.…”

Section: Experimental Design and Evaluationmentioning

confidence: 99%

A microcosmic syndrome differentiation model for metabolic syndrome with multi-label learning

Xia

Zhang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Metabolic Syndrome (MS) is a complex multi-system disease. Traditional Chinese medicine (TCM) is satisfactory in preventing and treating MS. Syndrome differentiation is the basis of TCM treatment, which is composed of location and/or nature syndrome elements. Many studies have found TCM syndromes are correlated with biological indicators. However, there are various data that mainly come from point-to-point studies, which can’t fully summarize the many to many relationship of TCM syndromes and biological indicators. Thus, it is also hard to deal with the problem that several types of syndromes may possibly happen to a patient at once in the real world. The purpose of this study is to find out the potential relationship between microcosmic index and syndrome elements from a holistic view by means of multi-label learning (MLL) technique, and to provide a multi-label model for TCM syndrome differentiation. Methods: The standardization scale on TCM four diagnostic information for MS is designed, which is used to obtain the results of TCM diagnosis. The model of microcosmic syndrome differentiation is constructed based on 39 physicochemical indexes, such as BMI, abdominal circumference, blood pressure，platelet，fasting blood sugar, insulin, blood lipid，by MLL techniques, called ML-kNN. First, the multi-label learning method is compared with three commonly used single learning algorithms. Then, the comparison of results of ML-kNN between physicochemical indexes and TCM information is also made. Next. the influence of parameter k of ML-kNN to the diagnostic model is investigated and then the best k-value is chosen for the TCM diagnosis. Results: A total of 698 cases are collected for the modeling of the microcosmic diagnosis of MS. The comprehensive performance of the ML-kNN model works obviously better than the others, whose average precision of diagnosis reach 71.4%. The results of ML-kNN based on microcosmic indexes are close to the results based on TCM information. The k value has less influence on the prediction results of ML- kNN. Conclusions: The MLL techniques facilitate building microcosmic syndrome differentiation model in MS and the experiments show this is a practical approach to solve the problem of labeling multiple syndromes simultaneously. Besides, it is also suggested that there is many to many relationships between TCM syndrome elements and physicochemical indexes, which will be conducive to the future objective and comprehensive study of syndrome differentiation in MS.

show abstract

Manifold regularized discriminative feature selection for multi-label learning

Cited by 246 publications

References 25 publications

Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets

Feature Selection for Multi-Label Learning Based on F-Neighborhood Rough Sets

Joint multilabel classification and feature selection based on deep canonical correlation analysis

A microcosmic syndrome differentiation model for metabolic syndrome with multi-label learning

Contact Info

Product

Resources

About