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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Unsupervised feature selection via unifying distribution alignment and structure preservation

文献类型：期刊论文

作者Cao, Chunxu2; Zhang, Yong1; Ai, Yanke1,4; Zhang, Qiang3,5
刊名INFORMATION FUSION
出版日期2026-02-01
卷号126页码:20
关键词Feature selection Filter feature selection method Distributional distances Gromov-Wasserstein distance Kernel trick Extreme gradient boosting
ISSN号1566-2535
DOI10.1016/j.inffus.2025.103544
英文摘要The increasing complexity of high-dimensional data demands effective feature selection techniques that preserve both global distributional characteristics and local structures. However, existing methods often encounter a fundamental trade-off between preserving global distributional fidelity and maintaining local geometric structures, leading to information loss. This work presents a novel kernel-enhanced Gromov-Wasserstein alignment framework that unifies global distribution alignment and local structure preservation. Our approach leverages Gromov-Wasserstein distance and the kernel trick to enhance metric space comparisons, effectively capturing nonlinear relationships while improving stability in noisy data. To ensure scalability, we develop an efficient randomized filter algorithm, balancing computational efficiency with feature diversity. Extensive experiments across 20 benchmark datasets demonstrate the superior performance of our method, showing that it surpasses state-of-the-art feature selection techniques. These results highlight the effectiveness of integrating distributional alignment and structure preservation for unsupervised feature selection in high-dimensional data analysis.
资助项目National Natural Science Foundation of China[12272054] ; Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science, BNU-HKBU United International College[2022B1212010006] ; Guangdong and Hong Kong Universities '1+1+1' Joint Research Collaboration Scheme
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001548072500002
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/41762]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Qiang
作者单位1.China Unicom, Unicom Digital Technol, Beijing 100013, Peoples R China
2.Beijing Normal Univ, Sch Math Sci, Beijing 100875, Peoples R China
3.Beijing Normal Hong Kong Baptist Univ, Guangdong Prov Key Lab Interdisciplinary Res & App, Zhuhai 519087, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
5.Beijing Normal Univ, Res Ctr Math, Zhuhai 519087, Peoples R China
推荐引用方式
GB/T 7714		 Cao, Chunxu,Zhang, Yong,Ai, Yanke,et al. Unsupervised feature selection via unifying distribution alignment and structure preservation[J]. INFORMATION FUSION,2026,126:20.
APA Cao, Chunxu,Zhang, Yong,Ai, Yanke,&Zhang, Qiang.(2026).Unsupervised feature selection via unifying distribution alignment and structure preservation.INFORMATION FUSION,126,20.
MLA Cao, Chunxu,et al."Unsupervised feature selection via unifying distribution alignment and structure preservation".INFORMATION FUSION 126(2026):20.

入库方式： OAI收割

来源：计算技术研究所

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。