• 论文 • 上一篇    

基于自步学习与稀疏自表达的半监督分类方法

古楠楠1,孙湘南1,刘伟2,李路云1   

  1. 1. 首都经济贸易大学统计学院,北京 100070; 2. 北京信息科技大学自动化学院, 北京 100192
  • 出版日期:2020-01-25 发布日期:2020-04-29

古楠楠,孙湘南,刘伟,李路云. 基于自步学习与稀疏自表达的半监督分类方法[J]. 系统科学与数学, 2020, 40(1): 191-208.

GU Nannan,SUN Xiangnan1,LIU Wei, LI Luyun. Semi-Supervised Classification Based on  Self-Paced Learning and Sparse Self-Expression[J]. Journal of Systems Science and Mathematical Sciences, 2020, 40(1): 191-208.

Semi-Supervised Classification Based on  Self-Paced Learning and Sparse Self-Expression

GU Nannan1 ,SUN Xiangnan1 ,LIU Wei2 ,LI Luyun1   

  • Online:2020-01-25 Published:2020-04-29

基于图的半监督分类方法近年来在模式识别和机器学习领域取得了广泛的关注. 然而许多传统方法在构建邻域图时采用固定的邻域尺寸, 且在模型训练过程 中同等对待所有样本, 忽略了样本间的差异性, 从而影响了方法的效果. 对此, 文章提出一种基于自步学习和稀疏自表达的半监督分类方法, 提取并保持数据的有判别信息的稀疏自表达结构, 并基于自步学习机制提出一种新的自步学习项, 将数据重要程度的软权重与硬权重相结合, 来对样本进行学习. 所提方法能够自适应建立数据间的关系, 自动给出样本的重要程度并由易到难进行学习, 且具有多类的显性非线性分类函数. 几个标准数据集上的实验结果表明, 所提算法具有较好的半监督分类效果.

Graph-based semi-supervised classification has attracted extensive attention in the field of pattern recognition and machine learning in recent years. However, many traditional methods use fixed neighborhood size when constructing neighborhood graph. Besides, they treat all samples equally in the process of model training, and ignore the differences among samples, which affects the effectiveness of the methods. In this paper, we propose a semi-supervised classification method based on self-paced learning and sparse self-expression. The method extracts and maintains the discriminative sparse self-expression structure of data, and proposes a new self-paced function based on self-paced learning mechanism, which combines the soft weight with the hard weight of data importance. The proposed method can adaptively establish the relationship between data points, and automatically give the data importance, which guides the learning process of partially labeled training data sequentially from the simple to the complex. Besides, the proposed method has multi-class explicit nonlinear classification function. The experimental results on several benchmark datasets show that the proposed algorithm has satisfactory semi-supervised classification effects.

()
[1] 李占芳,李慧云,刘新为. 分类稀疏低秩表示的子空间聚类方法[J]. 系统科学与数学, 2018, 38(8): 852-865.
[2] 张燕,张晨光,张夏欢. 平衡化图半监督学习方法[J]. 系统科学与数学, 2016, 36(8): 1107-1118.
[3] 蒋伟进,许宇晖,王欣. 基于成对约束的主动学习半监督谱聚类[J]. 系统科学与数学, 2013, 33(6): 708-723.
[4] 许洪贵;赵琨;田英杰. 鲁棒半监督$\nu$-支持向量分类机[J]. 系统科学与数学, 2010, 30(2): 265-273.
阅读次数
全文


摘要