Joint label-specific features and label correlation for multi-label learning with missing label

被引:37
作者
Cheng, Ziwei [1 ]
Zeng, Ziwei [1 ]
机构
[1] Univ Sci & Technol Liaoning, Anshan, Peoples R China
关键词
Missing labels; Label-specific features selections; Positive label correlations; Negative label correlations; CLASSIFICATION; SELECTION;
D O I
10.1007/s10489-020-01715-2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing multi-label learning classification algorithms ignore that class labels may be determined by some features in the original feature space. And only a partial label of each instance can be obtained for some real applications. Therefore, we propose a novel algorithm named joint Label-Specific features and Label Correlation for multi-label learning with Missing Label (LSLC-ML) and its optimized version to solve the above-mentioned problems. First, a missing label can be recovered by the learned positive and negative label correlations from the incomplete training data sets, then the label-specific features can be selected, finally the multi-label classification task can be modeled by combining the labelspecific feature selections, missing labels and positive and negative label correlations. The experimental results show that our algorithm LSLC-ML has strong competitiveness compared with some state-of-the-art algorithms in evaluation matrices when tested on benchmark multi-label data sets.
引用
收藏
页码:4029 / 4049
页数:21
相关论文
共 42 条
[11]   Mutual information-based feature selection for multilabel classification [J].
Doquire, Gauthier ;
Verleysen, Michel .
NEUROCOMPUTING, 2013, 122 :148-155
[12]   Leveraging Label-Specific Discriminant Mapping Features for Multi-Label Learning [J].
Guo, Yumeng ;
Chung, Fulai ;
Li, Guozheng ;
Wang, Jiancong ;
Gee, James C. .
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2019, 13 (02)
[13]   Multi-Label Learning With Label Specific Features Using Correlation Information [J].
Han, Huirui ;
Huang, Mengxing ;
Zhang, Yu ;
Yang, Xiaogang ;
Feng, Wenlong .
IEEE ACCESS, 2019, 7 :11474-11484
[14]   Improving multi-label classification with missing labels by learning label-specific features [J].
Huang, Jun ;
Qin, Feng ;
Zheng, Xiao ;
Cheng, Zekai ;
Yuan, Zhixiang ;
Zhang, Weigang ;
Huang, Qingming .
INFORMATION SCIENCES, 2019, 492 :124-146
[15]   Multi-label classification by exploiting local positive and negative pairwise label correlation [J].
Huang, Jun ;
Li, Guorong ;
Wang, Shuhui ;
Xue, Zhe ;
Huang, Qingming .
NEUROCOMPUTING, 2017, 257 :164-174
[16]   Learning Label-Specific Features and Class-Dependent Labels for Multi-Label Classification [J].
Huang, Jun ;
Li, Guorong ;
Huang, Qingming ;
Wu, Xindong .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2016, 28 (12) :3309-3323
[17]  
Huang S.J., 2012, P AAAI C ART INT, P949
[18]   FR3: A Fuzzy Rule Learner for Inducing Reliable Classifiers [J].
Huehn, Jens Christian ;
Huellermeier, Eyke .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2009, 17 (01) :138-149
[19]   Distributed multi-label feature selection using individual mutual information measures [J].
Gonzalez-Lopez, Jorge ;
Ventura, Sebastian ;
Cano, Alberto .
KNOWLEDGE-BASED SYSTEMS, 2020, 188 (188)
[20]  
Jorge G-L, 2019, IEEE T NEURAL NETW L