| 基于自编码器及超图学习的多标签特征提取 |
| |
| 引用本文： | 唐朝辉,朱清新,洪朝群,祝峰.基于自编码器及超图学习的多标签特征提取[J].自动化学报,2016,42(7):1014-1021. |
| |
| 作者姓名： | 唐朝辉 朱清新 洪朝群 祝峰 |
| |
| 作者单位： | 1.电子科技大学信息与软件工程学院 成都 611731 |
| |
| 基金项目： | 国家自然科学基金（61300192，61472110，61573297，61379049），中央高校基本科研项目（ZYGX2014J052），福建省自然科学基金（2014J01256，2015J01277）资助 |
| |
| 摘 要： | 在实际应用场景中越来越多的数据具有多标签的特性，且特征维度较高，包含大量冗余信息.为提高多标签数据挖掘的效率，多标签特征提取已经成为当前研究的热点.本文采用去噪自编码器获取多标签数据特征空间的鲁棒表达，在此基础上结合超图学习理论，融合多个标签对样本间几何关系的影响以提升特征提取的性能，构建多标签数据样本间几何关系所对应超图的Laplacian矩阵，并通过Laplacian矩阵的特征值分解得到低维投影空间.实验结果证明了本文所提出的算法在分类性能上是有效可行的.
|
| 关 键 词： | 深度学习 自编码器 多标签 超图 特征提取 |
| 收稿时间： | 2015-11-09 |
Multi-label Feature Selection with Autoencoders and Hypergraph Learning |
| |
| TANG Chao-Hui,ZHU Qing-Xin,HONG Chao-Qun,ZHU William.Multi-label Feature Selection with Autoencoders and Hypergraph Learning[J].Acta Automatica Sinica,2016,42(7):1014-1021. |
| |
| Authors: | TANG Chao-Hui ZHU Qing-Xin HONG Chao-Qun ZHU William |
| |
| Affiliation: | 1.School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 6117312.School of Computer and Information Engineering, Xiamen University of Technology, Xiamen 3610243.Laboratory of Granular Computing, Minnan Normal University, Zhangzhou 363000 |
| |
| Abstract: | In practical application scenarios, more and more data tend to be assigned with multiple labels and contain much redundant information in the high dimensional feature space. To improve the efficiency and effectiveness of multi-label data mining, multi-label data feature selection has become a hotspot. This paper utilizes denoising autoencoders to obtain a more robust version of multi-label data feature representation. Furthermore, based on hypergraph learning theory, a hypergraph Laplacian matrix corresponding to multi-label data is constructed by fusing the effects of all labels on geometrical relationship among all the samples, and then a projection space with lower dimension is obtained by conducting eigenvalue decomposition of the Laplacian matrix. Experimental results demonstrate the effectiveness and feasibility of the proposed algorithm according to its multi-label data classification performance. |
| |
| Keywords: | Deep learning autoencoders multi-label hypergraph feature selection |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
