ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2021, Vol. 58 ›› Issue (1): 34-47.doi: 10.7544/issn1000-1239.2021.20190674

• 人工智能 • 上一篇    下一篇

特征特定标记关联挖掘的类属属性学习

程玉胜1,2, 张露露1, 王一宾1,2, 裴根生1   

  1. 1(安庆师范大学计算机与信息学院 安徽安庆 246133);2(计算智能与信号处理教育部重点实验室(安徽大学) 合肥 230601) (chengyshaq@163.com)
  • 出版日期: 2021-01-01
  • 基金资助: 
    国家自然科学基金面上项目(61702012);计算智能与信号处理教育部重点实验室(安徽大学)项目(2020A003)

Label-Specific Features Learning for Feature-Specific Labels Association Mining

Cheng Yusheng1,2, Zhang Lulu1, Wang Yibin1,2, Pei Gensheng1   

  1. 1(School of Computer and Information, Anqing Normal University, Anqing, Anhui 246133);2(Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education, Hefei 230601)
  • Online: 2021-01-01
  • Supported by: 
    This work was supported by the General Program of the National Natural Science Foundation of China(61702012) and the Fund of Key Laboratory of Intelligent Computing & Signal Processing(Anhui University), Ministry of Education (2020A003).

摘要: 在多标记分类中,某个标记可能只由其自身的某些特有属性决定,这些特定属性称之为类属属性.利用类属属性进行多标记分类,可以有效避免某些无用特征影响构建分类模型的性能.然而类属属性算法仅从标记角度去提取重要特征,而忽略了从特征角度去提取重要标记.事实上,如果能从特征角度提前关注某些标记,更容易获取这些标记的特有属性.基于此,提出了一种新型类属属性学习的多标记分类算法,将从特征层面提取重要标记与从标记层面提取重要特征进行双向联合学习.首先,为了保证模型求解速度与精度都较为合理,采用极限学习机构建学习模型.随后,将弹性网络正则化理论添加到极限学习机损失函数中,使用互信息构建特征标记相关性矩阵作为L\-2正则化项,而L\-1正则化项即提取类属属性.该学习模型改进了类属属性在多标记学习中的不足,通过在标准多标记数据集上与多个先进算法对比,实验结果表明了所提模型的合理性和有效性.

关键词: 多标记学习, 类属属性, 特征特定标记, 极限学习机, 标记相关性

Abstract: In multi-label learning, a label may be determined by its own set of unique features only, which are called label-specific features. Using label-specific features in multi-label classification can effectively avoid some useless features affecting the performance of the constructed classification model. However, existing label-specific features methods only extract important features from the label’s perspective, while ignoring extracting important labels from the feature’s perspective. In fact, it’s easier to extract the unique features for labels by focusing on certain labels from the feature’s perspective. Based on this, a novel label-specific features learning algorithm for multi-label classification is proposed. It combines the label’s important features with the feature’s important labels. Firstly, in order to ensure the efficiency and accuracy of the model, the extreme learning machine is used to construct the joint learning model. Subsequently, the elastic network regularization theory is applied to the extreme learning machine’s loss function, and the mutual information theory is used to construct the correlation matrix of feature-specific labels as the L\-2 regularization term, and the label-specific features are extracted by the L\-1 regularization term. The learning model improves the deficiencies of label-specific features and the adaptability of the extreme learning machine in multi-label learning. Compared with several state-of-the-art algorithms on several benchmark multi-label datasets, the experimental results show the rationality and effectiveness of the proposed model.

Key words: multi-label learning, label-specific features, feature-specific labels, extreme learning machine, label correlation

中图分类号: