An improved MLTSVM using label-specific features with missing labels

被引:6
|
作者
Ai, Qing [1 ]
Li, Fei [1 ]
Li, Xiangna [2 ]
Zhao, Ji [1 ]
Wang, Wenhui [3 ]
Gao, Qingyun [1 ]
Zhao, Fei [1 ]
机构
[1] Univ Sci & Technol Liaoning, Sch Comp Sci & Software Engn, Anshan 114051, Peoples R China
[2] State Grid Corp China, State Grid Informat & Telecommun Grp Co Ltd, Beijing 100053, Peoples R China
[3] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China
关键词
Multi-label classification; Label-specific features; Missing labels; MLTSVM; SUPPORT VECTOR MACHINE; CLASSIFICATION; FRAMEWORK; SELECTION;
D O I
10.1007/s10489-022-03634-w
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-label twin support vector machine (MLTSVM) is an excellent multi-label classification algorithm, which has attracted much attention. Although MLTSVM can effectively solve the multi-label classification problem, it has some drawbacks. a) MLTSVM uses the same feature representation for each label, but in practice, each label has its own specific features. Therefore, MLTSVM might not obtain the optimal classification results. b) In practical applications, there are a large number of samples with missing labels and only a small number of samples with complete labels, because it is expensive to obtain all labels of samples. However, MLTSVM can only use expensive samples with complete labels, not cheap samples with missing labels. For the above drawbacks, we propose an improved MLTSVM using label-specific features with missing labels (LSFML-MLTSVM) in this paper. LSFML-MLTSVM first extracts label-specific features via using semi-supervised clustering analysis and then obtains the structure information of samples and the geometry information of the marginal distribution. Furthermore, in the label-specific feature space, the above two valuable information is introduced into MLTSVM to reconstruct the classification model. Finally, the successive overrelaxation (SOR) algorithm is used to solve the classification model efficiently. Experimental results on benchmark multi-label datasets show that LSFML-MLTSVM has better classification performance.
引用
收藏
页码:8039 / 8060
页数:22
相关论文
共 50 条
  • [31] Multi-label space reshape for semantic-rich label-specific features learning
    Cheng, Yusheng
    Zhang, Chao
    Pang, Shufang
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2022, 13 (04) : 1005 - 1019
  • [32] Leveraging Label-Specific Discriminant Mapping Features for Multi-Label Learning
    Guo, Yumeng
    Chung, Fulai
    Li, Guozheng
    Wang, Jiancong
    Gee, James C.
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2019, 13 (02)
  • [33] Label distribution feature selection based on label-specific features
    Shu, Wenhao
    Xia, Qiang
    Qian, Wenbin
    APPLIED INTELLIGENCE, 2024, 54 (19) : 9195 - 9212
  • [34] Learning label-specific features with global and local label correlation for multi-label classification
    Weng, Wei
    Wei, Bowen
    Ke, Wen
    Fan, Yuling
    Wang, Jinbo
    Li, Yuwen
    APPLIED INTELLIGENCE, 2023, 53 (03) : 3017 - 3033
  • [35] Learning label-specific features with global and local label correlation for multi-label classification
    Wei Weng
    Bowen Wei
    Wen Ke
    Yuling Fan
    Jinbo Wang
    Yuwen Li
    Applied Intelligence, 2023, 53 : 3017 - 3033
  • [36] Exploring Common and Label-Specific Features for Multi-Label Learning With Local Label Correlations
    Ling, Yunzhi
    Wang, Ying
    Wang, Xin
    Ling, Yunhao
    IEEE ACCESS, 2020, 8 : 50969 - 50982
  • [37] Bi-directional mapping for multi-label learning of label-specific features
    Tan, Yi
    Sun, Dong
    Shi, Yu
    Gao, Liuya
    Gao, Qingwei
    Lu, Yixiang
    APPLIED INTELLIGENCE, 2022, 52 (07) : 8147 - 8166
  • [38] Soft-label recover based label-specific features learning
    Jiang, Jiansheng
    Ge, Wenxin
    Wang, Yibin
    Cheng, Yusheng
    Xu, Yuting
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [39] Weakly-supervised label distribution feature selection via label-specific features and label correlation
    Shu, Wenhao
    Hu, Jiayu
    Qian, Wenbin
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, : 2181 - 2201
  • [40] Joint Lable-Density-Margin Space and Extreme Elastic Net for Label-Specific Features
    Pei, Gensheng
    Wang, Yibin
    Cheng, Yusheng
    Zhang, Lulu
    IEEE ACCESS, 2019, 7 : 112304 - 112317