基于改进松弛嵌入空间的多视图聚类  

MULTIPLE VIEW CLUSTERING BASED ON IMPROVED SLACK EMBEDDING SPACE

作　　者：张瑛[1] Zhang Ying(School of Automotive and Information Engineering,Taizhou Vocational College of Science&Technology,Taizhou 318000,Zhejiang,China)

机构地区：[1]台州科技职业学院汽车与信息工程学院,浙江台州318000

出　　处：《计算机应用与软件》2024年第4期275-283,共9页Computer Applications and Software

基　　金：浙江省教育科学规划课题(2013CG423);台州科技职业学院校级常规课题(2020CG017)。

摘　　要：针对传统聚类方法缺乏统一特征表示,存在保守性的缺陷,提出一种基于改进松弛嵌入空间的多视图聚类方法。在统一的框架下联合学习一个综合的潜在嵌入表示矩阵、全局相似矩阵和一个精确指标矩阵。进一步放松全局相似矩阵的约束,并在此基础上提出一种改进的松弛多视图聚类嵌入空间,使得该方法具有更低的计算复杂度和更多的数据点对之间的相关性。实验结果表明,该方法能够获得鲁棒性更强、准确度更高的聚类结果。In view of the lack of unified feature representation and defects of conservatism of traditional clustering methods,a multiple view clustering method based on improved slack embedding space is proposed.In a unified framework,a comprehensive potential embedding representation matrix,a global similarity matrix and an accurate index matrix were jointly learned.Furthermore,the constraint of global similarity matrix was slack,and an improved slack multiple view clustering embedding space was proposed,which made the proposed method have lower computational complexity and more correlation between data point pairs.The experimental results show that the proposed method can obtain more robust and more accurate clustering results.

关 键 词：多视图聚类 嵌入空间 相似矩阵 松弛因子 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术]