Multi-dimensional Classification via Selective Feature Augmentation

doi:10.1007/s11633-022-1316-5

	Multi-dimensional Classification via Selective Feature Augmentation
	Jia, Bin-Bin1,2,3 ; Zhang, Min-Ling 1,3
	2022-02
发表期刊	Machine Intelligence Research
ISSN	2153-182X
卷号	19 期号:1 页码:38-51
摘要	In multi-dimensional classification (MDC), the semantics of objects are characterized by multiple class spaces from different dimensions. Most MDC approaches try to explicitly model the dependencies among class spaces in output space. In contrast, the recently proposed feature augmentation strategy, which aims at manipulating feature space, has also been shown to be an effective solution for MDC. However, existing feature augmentation approaches only focus on designing holistic augmented features to be appended with the original features, while better generalization performance could be achieved by exploiting multiple kinds of augmented features. In this paper, we propose the selective feature augmentation strategy that focuses on synergizing multiple kinds of augmented features. Specifically, by assuming that only part of the augmented features is pertinent and useful for each dimension’s model induction, we derive a classification model which can fully utilize the original features while conduct feature selection for the augmented features. To validate the effectiveness of the proposed strategy, we generate three kinds of simple augmented features based on standard kNN, weighted kNN, and maximum margin techniques, respectively. Comparative studies show that the proposed strategy achieves superior performance against both state-of-the-art MDC approaches and its degenerated versions with either kind of augmented features. © 2022, The Author(s).
关键词	Classification (of information) Machine learning Semantics Class dependency Class spaces Classification models Effective solution Feature augmentation Feature space Features selection Generalization performance Multiple class S models
DOI	10.1007/s11633-022-1316-5
收录类别	EI ; ESCI
语种	英语
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence
WOS记录号	WOS:000799088200004
出版者	Chinese Academy of Sciences
EI入藏号	20220511539616
EI主题词	Feature extraction
EI分类号	716.1 Information Theory and Signal Processing ; 903.1 Information Sources and Analysis
来源库	WOS
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/157991
专题	电气工程与信息工程学院
通讯作者	Zhang, Min-Ling
作者单位	1.Southeast Univ, Sch Comp Sci & Engn, Nanjing 210096, Peoples R China; 2.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Peoples R China; 3.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing, Peoples R China
第一作者单位	电气工程与信息工程学院
推荐引用方式 GB/T 7714	Jia, Bin-Bin,Zhang, Min-Ling. Multi-dimensional Classification via Selective Feature Augmentation[J]. Machine Intelligence Research,2022,19(1):38-51.
APA	Jia, Bin-Bin,&Zhang, Min-Ling.(2022).Multi-dimensional Classification via Selective Feature Augmentation.Machine Intelligence Research,19(1),38-51.
MLA	Jia, Bin-Bin,et al."Multi-dimensional Classification via Selective Feature Augmentation".Machine Intelligence Research 19.1(2022):38-51.