基于Hessian正则的自适应损失半监督特征选择
CSTR:
作者:
作者单位:

1. 华东交通大学 电气与自动化工程学院,南昌 330013;2. 江西省先进控制与优化重点实验室,quad 南昌 330013;3. 西北工业大学 光学影像分析与学习中心,西安 710072

作者简介:

通讯作者:

E-mail: yhshuo@263.net.

中图分类号:

TP391

基金项目:

国家自然科学基金重点项目(61733005);国家自然科学基金项目(61563015,61963015,61863014);江西省自然科学基金项目(20171ACB21039,20192BAB207024);江西省教育厅科技项目(GJJ150552).


Adaptive loss semi-supervised feature selection based on Hessian regularization
Author:
Affiliation:

1. College of Electrical and Automation,East China Jiaotong University,Nanchang 330013,China;2. Key Laboratory of Advanced Control and Optimization of Jiangxi Province,Nanchang 330013,China;3. Center for Optical Image Analysis and Learning,Northwestern Polytechnical University,Xián 710072,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    传统的基于拉普拉斯图的半监督特征选择算法处理高维、少标签样本时,缺乏外推能力且对数据异常值的鲁棒性差.基于此,提出一种基于Hessian正则的自适应损失半监督稀疏特征选择算法.首先,为提升线性映射能力,利用Hessian正则保留数据的局部流形结构;其次,为增强模型对具有较小或者较大损失数据的鲁棒性,引入自适应损失函数,通过调节自适应损失参数确定最小损失;再次,采用$l_{2,p

    Abstract:

    The traditional semi-supervised sparse feature selection based on Laplacian graph has received extensive attention for its higher efficiency. However, due to the lack of extrapolation ability of the Laplacian operator, the limited labeled data is still not well utilized and is too sensitive for outliers. Therefore, an adaptive loss semi-supervised sparse feature selection algorithm based on Hessian regularization is proposed. Firstly, Hessian is used to preserve the local manifold structure of data in order to improve the linear mapping capability. At the same time, an adaptive loss function is exploited to measure the label fitness by adjusting the adaptive loss parameters, which significantly enhances model's robustness to data with a small or substantial loss. Moreover, $l_{2,p

    参考文献
    相似文献
    引证文献
引用本文

朱建勇,周振辰,杨辉,等.基于Hessian正则的自适应损失半监督特征选择[J].控制与决策,2021,36(8):1862-1870

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-07-13
  • 出版日期: 2021-08-20
文章二维码