Label-noise robust classification with multi-view learning

被引:1
作者
Liang, NaiYao [1 ]
Yang, ZuYuan [1 ]
Li, LingJiang [1 ,2 ]
Li, ZhenNi [1 ,3 ]
Xie, ShengLi [1 ]
机构
[1] Guangdong Univ Technol, Sch Automat, Guangdong Key Lab IoT Informat Technol, Guangzhou 510006, Peoples R China
[2] Minist Educ, Key Lab IDetect & Mfg IoT, Guangzhou 510006, Peoples R China
[3] Guangdong HongKong Macao Joint Lab Smart Discrete, Guangzhou 510006, Peoples R China
基金
中国国家自然科学基金;
关键词
label noise; multi-view learning; classification; robust; least squares regression; label relaxation;
D O I
10.1007/s11431-021-2139-0
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Label noise is often contained in the training data due to various human factors or measurement errors, which significantly causes a negative effect on classifiers. Despite many previous methods that have been proposed to learn robust classifiers, they are mainly based on the single-view feature. On the other hand, although existing multi-view classification methods benefit from the more comprehensive information, they rarely consider label noise. In this paper, we propose a novel label-noise robust classification model with multi-view learning to overcome these limitations. In the proposed model, not only the classifier learning but also the label-noise removal can benefit from the multi-view information. Specifically, we relax the label matrix of the basic multi-view least squares regression model, and develop a nonlinear transformation with a natural probabilistic approximation in the process of labels, which is conveniently optimized and beneficial to improve the discriminative ability of classifiers. Moreover, we preserve the intrinsic manifold structure of multi-view data on the relaxed label matrix, facilitating the process of label relaxation. For optimizing the proposed model with the nonlinear transformation, we derive a lemma about the partial derivation of the softmax related function, and develop an efficient alternating algorithm. Experimental evaluations on six real-world datasets confirm the advantages of the proposed method, compared to the related state-of-the-art methods.
引用
收藏
页码:1841 / 1854
页数:14
相关论文
共 50 条
  • [41] A new multi-view multi-label model with privileged information learning
    Xiao, Yanshan
    Chen, Junfeng
    Liu, Bo
    Zhao, Liang
    Kong, Xiangjun
    Hao, Zhifeng
    INFORMATION SCIENCES, 2024, 656
  • [42] Multi-view multi-label active learning with conditional Bernoulli mixtures
    Jing Zhao
    Zengyu Qiu
    Shiliang Sun
    International Journal of Machine Learning and Cybernetics, 2022, 13 : 1589 - 1601
  • [43] Multi-view Multi-label Learning via Optimal Classifier Chain
    Liu, Yiming
    Hao, Xingwei
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT I, 2018, 10735 : 336 - 345
  • [44] Multi-view multi-label active learning with conditional Bernoulli mixtures
    Zhao, Jing
    Qiu, Zengyu
    Sun, Shiliang
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2022, 13 (06) : 1589 - 1601
  • [45] A Reconstruction Error Based Framework for Multi-Label and Multi-View Learning
    Qian, Buyue
    Wang, Xiang
    Ye, Jieping
    Davidson, Ian
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2015, 27 (03) : 594 - 607
  • [46] Consistent and specific multi-view multi-label learning with correlation information
    Li, Yiting
    Zhang, Jia
    Wu, Hanrui
    Du, Guodong
    Long, Jinyi
    INFORMATION SCIENCES, 2025, 687
  • [47] Error-Robust Multi-View Clustering
    Najafi, Mehrnaz
    He, Lifang
    Yu, Philip S.
    2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2017, : 736 - 745
  • [48] Differentiable Hierarchical Optimal Transport for Robust Multi-View Learning
    Luo, Dixin
    Xu, Hongteng
    Carin, Lawrence
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (06) : 7293 - 7307
  • [49] Image classification with multi-view multi-instance metric learning
    Tang, Jingjing
    Li, Dewei
    Tian, Yingjie
    EXPERT SYSTEMS WITH APPLICATIONS, 2022, 189
  • [50] Robust Unsupervised Multi-View Feature Learning With Dynamic Graph
    Li, Yikun
    Liu, Li
    Shi, Dan
    Cui, Hui
    Lu, Xu
    IEEE ACCESS, 2019, 7 : 72197 - 72209