检索结果-内蒙古大学图书馆

graph-regularized consensus learning and Diversity Representation for unsupervised multi-view feature selection

KNOWLEDGE-BASED SYSTEMS 2025年 311卷

作者： Xu, Shengke Xie, Xijiong Cao, Zhiwen Ningbo Univ Sch Informat Sci & Engn Ningbo 315211 Peoples R China Key Lab Mobile Network Applicat Technol Zhejiang P Ningbo 315211 Peoples R China

In the existing data dimensionality reduction methods, unsupervised multi-view feature selection has been widely adopted for its effectiveness. However, most of the current methods lack sufficient integration of consensus and complementarity principles. On the one hand, some methods focus solely on the consensus representation of multiple views and neglect the inter-view complementarity and the uniqueness of each view. On the other hand, some methods obtain intrinsic representation matrices for each view and combine them crudely to form the final result, which fails to exploit complementary information among views. Inspired by these two aspects, this paper proposes the graph-regularized consensus learning and Diversity Representation (GCDUFS) for unsupervised multi-view feature selection. The algorithm leverages graph regularization to constrain the consensus matrix, better capturing common manifold information. It also utilizes kernel functions to measure the dependency of the data in the Hilbert space, effectively capturing the diverse information across all views. Additionally, symmetric non-negative matrix factorization (SNMF) is employed for clustering analysis. The above-mentioned methods are smoothly integrated into a unified model framework, and the GCDUFS algorithm is optimized using the alternating direction method of multipliers (ADMM) minimization strategy. Through the analysis of nine multi-view datasets, we conducted comprehensive clustering experiments and verified that our proposed method outperforms several state-of-the-art competitors in terms of performance.

关键词： Unsupervised multi-view feature selection graph-regularized consensus learning Independent diversity Subspace learning Clustering structure

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：