A label-specific multi-label feature selection algorithm based on the Pareto dominance concept

被引:60
作者
Kashef, Shima [1 ,2 ]
Nezamabadi-pour, Hossein [1 ,2 ]
机构
[1] Shahid Bahonar Univ Kerman, Dept Elect Engn, Intelligent Data Proc Lab, POB 76619-133, Kerman, Iran
[2] Shahid Bahonar Univ Kerman, Mahani Math Res Ctr, Kerman, Iran
关键词
Multi-label dataset; Feature selection; Label-specific features; Pareto dominance; Online feature selection; MUTUAL INFORMATION; CLASSIFICATION; TRANSFORMATION;
D O I
10.1016/j.patcog.2018.12.020
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In multi-label data, each instance is associated with a set of labels, instead of one label. Similar to single-label data, feature selection plays an important role in improving classification performance. In multi-label classification, each class label might be specified by some particular characteristics of its own which are called label-specific features. In this paper, a fast accurate filter-based feature selection method is exclusively designed for multi-label datasets to find label-specific features. It maps the features to a multi-dimensional space based on a filter method, and selects the most salient features with the help of Pareto-dominance concepts from multi-objective optimization domain. Our proposed method can be used as online feature selection that deals with problems in which features arrive sequentially while the number of data samples is fixed. In this method, the number of features to be selected is specified during the process of feature selection. However, sometimes it is desired to predefine the number of features. For this reason, an extension of the proposed method is presented to solve this problem. To prove the performance of the proposed methods, several experiments are conducted on some multi-label datasets and the results are compared to five well-established multi-label feature selection methods. The results show the superiority of the proposed methods in terms of different multi-label classification criteria and execution time. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码:654 / 667
页数:14
相关论文
共 52 条
[1]   A Clustering Based Archive Multi Objective Gravitational Search Algorithm [J].
Abbasian, Mohammad Amir ;
Nezamabadi-pour, Hossein ;
Amoozegar, Maryam .
FUNDAMENTA INFORMATICAE, 2015, 138 (04) :387-409
[2]   KEEL: a software tool to assess evolutionary algorithms for data mining problems [J].
Alcala-Fdez, J. ;
Sanchez, L. ;
Garcia, S. ;
del Jesus, M. J. ;
Ventura, S. ;
Garrell, J. M. ;
Otero, J. ;
Romero, C. ;
Bacardit, J. ;
Rivas, V. M. ;
Fernandez, J. C. ;
Herrera, F. .
SOFT COMPUTING, 2009, 13 (03) :307-318
[3]  
[Anonymous], 2013, IBEROAMERICAN C PATT, DOI DOI 10.1007/978-3-642-41827-3.66
[4]  
[Anonymous], 2008, ISMIR
[5]  
Biesiada J., 2005, INT C RES EL APPL IN, P1
[6]   Learning multi-label scene classification [J].
Boutell, MR ;
Luo, JB ;
Shen, XP ;
Brown, CM .
PATTERN RECOGNITION, 2004, 37 (09) :1757-1771
[7]   Document transformation for multi-label feature selection in text categorization [J].
Chen, Weizhu ;
Yan, Jun ;
Zhang, Benyu ;
Chen, Zheng ;
Yang, Qiang .
ICDM 2007: PROCEEDINGS OF THE SEVENTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, 2007, :451-+
[8]   Lazy Multi-label Learning Algorithms Based on Mutuality Strategies [J].
Cherman, Everton Alvares ;
Spolaor, Newton ;
Valverde-Rebaza, Jorge ;
Monard, Maria Carolina .
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2015, 80 :S261-S276
[9]   Mutual information-based feature selection for multilabel classification [J].
Doquire, Gauthier ;
Verleysen, Michel .
NEUROCOMPUTING, 2013, 122 :148-155
[10]  
Doquire G, 2011, LECT NOTES COMPUT SC, V6691, P9, DOI 10.1007/978-3-642-21501-8_2