中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
fi-divergence NMF with biorthogonal regularization for data representation

文献类型：期刊论文

作者Yuan, Ruixue2; Leng, Chengcai2; Li, Bing3; Basu, Anup1
刊名ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
出版日期2023-05-01
卷号121页码:14
ISSN号0952-1976
关键词NMF fi-divergence Biorthogonal regularization Clustering
DOI10.1016/j.engappai.2023.106014
通讯作者Leng, Chengcai(ccleng@nwu.edu.cn)
英文摘要Non-Negative Matrix Factorization (NMF) has become a commonly used method for data representation. Orthogonal NMF improves the clustering performance by adding orthogonal constraints to the decomposed matrices. The existing orthogonal NMF methods typically use Euclidean distance to measure the difference between before and after factorization for convenience and simplicity. However, limitations of the Euclidean distance can lead to inflexibilities. In addition, failure to consider orthogonality of the decomposed features and sparsity of the data representation can also lead to degraded performance of the algorithm. In order to overcome the above shortcomings, we propose a novel fi-divergence-based NMF with biorthogonal regularization (BO-fi NMF). Our BO-fi NMF method uses generalized fi-divergence instead of Euclidean distance to measure the similarity between matrices, and selects an appropriate fi for each type of data to obtain a more flexible way of measuring similarity. In addition, we also incorporate biorthogonal constraints into the minimized objective function, which ensures both orthogonality of the decomposed features and sparsity of the data representation. Furthermore, we use trace rather than Euclidean distance to measure the orthogonality of the decomposed matrices, which reduces execution time. Finally, clustering experiments on image datasets show that the overall clustering effect of BO-fi NMF is better than state-of-the-art methods.
WOS关键词NONNEGATIVE MATRIX FACTORIZATION ; ROBUST ; ALGORITHMS
资助项目National Natural Science Foundation of China[61702251] ; Natural Science Basic Research Plan in Shaanxi Province of China[2018JM6030] ; Natural Sciences and Engineering Research Council of Canada ; Youth Academic Talent Support Program of Northwest University, China[360051900151]
WOS研究方向Automation & Control Systems ; Computer Science ; Engineering
语种英语
出版者PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号WOS:000990904700001
资助机构National Natural Science Foundation of China ; Natural Science Basic Research Plan in Shaanxi Province of China ; Natural Sciences and Engineering Research Council of Canada ; Youth Academic Talent Support Program of Northwest University, China
源URL[http://ir.ia.ac.cn/handle/173211/53275]  
专题多模态人工智能系统全国重点实验室
通讯作者Leng, Chengcai
作者单位1.Univ Alberta, Dept Comp Sci, Edmonton, AB 628, Canada
2.Northwest Univ, Sch Math, Xian 710127, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Yuan, Ruixue,Leng, Chengcai,Li, Bing,et al. fi-divergence NMF with biorthogonal regularization for data representation[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2023,121:14.
APA Yuan, Ruixue,Leng, Chengcai,Li, Bing,&Basu, Anup.(2023).fi-divergence NMF with biorthogonal regularization for data representation.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,121,14.
MLA Yuan, Ruixue,et al."fi-divergence NMF with biorthogonal regularization for data representation".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 121(2023):14.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。