计算机应用 ›› 2021, Vol. 41 ›› Issue (1): 8-14.DOI: 10.11772/j.issn.1001-9081.2020060971

所属专题: 第八届中国数据挖掘会议(CCDM 2020)

• 第八届中国数据挖掘会议(CCDM 2020) • 上一篇    下一篇

图趋势过滤诱导的噪声容错多标记学习模型

林腾涛1, 查思明1, 陈蕾1,2, 龙显忠1   

  1. 1. 南京邮电大学 计算机学院、软件学院、网络安全学院, 南京 210003;
    2. 江苏省大数据安全与智能处理重点实验室(南京邮电大学), 南京 210003
  • 收稿日期:2020-05-31 修回日期:2020-07-16 出版日期:2021-01-10 发布日期:2020-09-02
  • 通讯作者: 陈蕾
  • 作者简介:林腾涛(1995-),男,江苏南京人,硕士研究生,主要研究方向:机器学习;查思明(1996-)男,江苏淮安人,硕士研究生,主要研究方向:机器学习;陈蕾(1975-),男,江西宜春人,教授,博士,CCF会员,主要研究方向:大规模机器学习、模式识别、数据挖掘;龙显忠(1981-),男,河南光山人,副教授,博士,主要研究方向:计算机视觉、机器学习、图像处理。
  • 基金资助:
    国家自然科学基金资助项目(61872190)。

Graph trend filtering guided noise tolerant multi-label learning model

LIN Tengtao1, ZHA Siming1, CHEN Lei1,2, LONG Xianzhong1   

  1. 1. School of Computer Science, Software and Network Security, Nanjing University of Posts and Telecommunications, Nanjing Jiangsu 210003, China;
    2. Jiangsu Key Laboratory of Big Data Security and Intelligent Processing(Nanjing University of Posts and Telecommunications), Nanjing Jiangsu 210003, China
  • Received:2020-05-31 Revised:2020-07-16 Online:2021-01-10 Published:2020-09-02
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61872190).

摘要: 针对多标记学习中特征噪声和标记噪声经常共同出现的问题,提出了一种图趋势过滤诱导的噪声容错多标记学习模型(GNTML)。该模型通过组稀疏约束桥接增强的标记,从而同时容忍特征噪声和标记噪声。模型的关键之处在于标记增强矩阵的学习。为了在混合噪声场景下学习到合理的标记增强矩阵,首先通过引入图趋势过滤(GTF)机制来容忍含噪示例特征与标记之间关联的不一致性,从而减轻特征噪声对标记增强矩阵学习的影响;然后通过引入组稀疏约束的标记保真惩罚来减轻标记噪声对标记增强矩阵学习的影响,同时引入标记关联矩阵的稀疏约束来刻画标记之间的局部关联特性,使得样本标记能够在相似样本之间得到更好的传播;最后在7个真实多标记数据集上进行5个不同评价指标下的实验。实验结果表明,提出的模型在66.67%的情况下取得最优值或次优值,优于其他5个多标记学习算法,能有效地提高多标记学习的鲁棒性。

关键词: 多标记学习, 噪声容错, 组稀疏, 标记增强, 图趋势过滤

Abstract: Focusing on the problem that the feature noise and label noise often appear simultaneously in multi-label learning, a Graph trend filtering guided Noise Tolerant Multi-label Learning (GNTML) model was proposed. In the proposed model, the feature noise and label noise were tolerated at the same time by group sparsity constraint bridged with label enrichment. The key of the model was the learning of the label enhancement matrix. In order to learn a reasonable label enhancement matrix in the mixed noise environment, the following steps were carried out. Firstly, the Graph Trend Filtering (GTF) mechanism was introduced to tolerate the inconsistency between the noisy example features and labels, so as to reduce the influence of the feature noise on the learning of the enhancement matrix. Then, the group sparsity constrained label fidelity penalty was introduced to reduce the impact of label noise on the label enhancement matrix learning. At the same time, the sparsity constraint of label correlation matrix was introduced to characterize the local correlation between the labels, so that the example labels were able to propagate better between similar examples. Finally, experiments were conducted on seven real multi-label datasets with five different evaluation criteria. Experimental results show that the proposed model achieves the optimal value or suboptimal value in 66.67% cases, it is better than other five multi-label learning algorithms, and can effectively improve the robustness of multi-label learning.

Key words: multi-label learning, noise tolerance, group sparsity, label enhancement, Graph Trend Filtering (GTF)

中图分类号: