计算机应用 ›› 2018, Vol. 38 ›› Issue (12): 3391-3398.DOI: 10.11772/j.issn.1001-9081.2018051050

• 人工智能 • 上一篇    下一篇

自适应嵌入的半监督多视角特征降维方法

孙圣姿, 万源, 曾成   

  1. 武汉理工大学 理学院, 武汉 430070
  • 收稿日期:2018-05-21 修回日期:2018-06-29 出版日期:2018-12-10 发布日期:2018-12-15
  • 通讯作者: 万源
  • 作者简介:孙圣姿(1996-),女,天津人,主要研究方向:机器学习、高维图像特征降维;万源(1976-),女,湖北武汉人,教授,博士,主要研究方向:机器学习、图像处理、高维图像特征降维;曾成(1997-),男,湖北武汉人,主要研究方向:机器学习、高维图像特征降维。
  • 基金资助:
    中央高校基本科研业务费专项资金项目(2018IB016)。

Semi-supervised adaptive multi-view embedding method for feature dimension reduction

SUN Shengzi, WAN Yuan, ZENG Cheng   

  1. School of Science, Wuhan University of Technology, Wuhan Hubei 430070, China
  • Received:2018-05-21 Revised:2018-06-29 Online:2018-12-10 Published:2018-12-15
  • Contact: 万源
  • Supported by:
    This work is partially supported by the Fundamental Research Funds for the Central Universities (2018IB016).

摘要: 半监督模式下的多视角特征降维方法,大多并未考虑到不同视角间特征投影的差异,且由于缺乏对降维后的低维矩阵的稀疏约束,无法避免噪声和其他不相关特征的影响。针对这两个问题,提出自适应嵌入的半监督多视角特征降维方法。首先,将投影从单视角下相同的嵌入矩阵扩展到多视角间不同的矩阵,引入全局结构保持项;然后,将无标签的数据利用无监督方法进行嵌入投影,对于有标签的数据,结合分类的判别信息进行线性投影;最后,再将两类多投影映射到统一的低维空间,使用组合权重矩阵来保留全局结构,很大程度上消除了噪声及不相关因素的影响。实验结果表明,所提方法的聚类准确率平均提高了约9%。该方法较好地保留了多视角间特征的相关性,捕获了更多的具有判别信息的特征。

关键词: 多视角特征降维, 半监督学习, 自适应性嵌入, 组合权重矩阵, 正则化稀疏约束

Abstract: Most of the semi-supervised multi-view feature reduction methods do not take into account of the differences in feature projections among different views, and it is not able to avoid the effects of noise and other unrelated features because of the lack of sparse constraints on the low-dimensional matrix after dimension reduction. In order to solve the two problems, a new Semi-Supervised Adaptive Multi-View Embedding method for feature dimension reduction (SS-AMVE) was proposed. Firstly, the projection was extended from the same embedded matrix in a single view to different matrices in multi-view, and the global structure maintenance term was introduced. Then, the unlabeled data was embedded and projected by the unsupervised method, and the labeled data was linearly projected in combination with the classified discrimination information. Finally, the two types of multi-projection were mapped to a unified low-dimensional space, and the combined weight matrix was used to preserve the global structure, which largely eliminated the effects of noise and unrelated factors. The experimental results show that, the clustering accuracy of the proposed method is improved by about 9% on average. The proposed method can better preserve the correlation of features between multiple views, and capture more features with discriminative information.

Key words: multi-view feature dimension reduction, semi-supervised learning, adaptive embedding, combined weight matrix, regularized sparse constraint

中图分类号: