CSpace  > 应用数学研究所
A Minimax Probability Machine for Nondecomposable Performance Measures
Luo, Junru1,2; Qiao, Hong3,4; Zhang, Bo5,6,7
2021-09-01
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
Pages13
AbstractImbalanced classification tasks are widespread in many real-world applications. For such classification tasks, in comparison with the accuracy rate (AR), it is usually much more appropriate to use nondecomposable performance measures such as the area under the receiver operating characteristic curve (AUC) and the $F_beta$ measure as the classification criterion since the label class is imbalanced. On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the AR, which makes it unsuitable to deal with imbalanced classification tasks. The purpose of this article is to develop a new minimax probability machine for the $F_beta$ measure, called minimax probability machine for the $F_beta$ -measures (MPMF), which can be used to deal with imbalanced classification tasks. A brief discussion is also given on how to extend the MPMF model for several other nondecomposable performance measures listed in the article. To solve the MPMF model effectively, we derive its equivalent form which can then be solved by an alternating descent method to learn a linear classifier. Further, the kernel trick is employed to derive a nonlinear MPMF model to learn a nonlinear classifier. Several experiments on real-world benchmark datasets demonstrate the effectiveness of our new model.
KeywordMeasurement Task analysis Covariance matrices Support vector machines Prediction algorithms Minimization Kernel Imbalanced classification minimax probability machine nondecomposable performance measures
DOI10.1109/TNNLS.2021.3106484
Indexed BySCI
Language英语
Funding ProjectNNSF of China[91948303] ; NNSF of China[61627808]
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000732226800001
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.amss.ac.cn/handle/2S8OKBNM/59728
Collection应用数学研究所
Corresponding AuthorZhang, Bo
Affiliation1.Changzhou Univ, Sch Comp Sci & Artificial Intelligence, Changzhou 213100, Jiangsu, Peoples R China
2.Changzhou Univ, Aliyun Sch Big Data, Changzhou 213100, Jiangsu, Peoples R China
3.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
5.Chinese Acad Sci, LSEC, Beijing 100190, Peoples R China
6.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China
7.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Luo, Junru,Qiao, Hong,Zhang, Bo. A Minimax Probability Machine for Nondecomposable Performance Measures[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:13.
APA Luo, Junru,Qiao, Hong,&Zhang, Bo.(2021).A Minimax Probability Machine for Nondecomposable Performance Measures.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA Luo, Junru,et al."A Minimax Probability Machine for Nondecomposable Performance Measures".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):13.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Luo, Junru]'s Articles
[Qiao, Hong]'s Articles
[Zhang, Bo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Luo, Junru]'s Articles
[Qiao, Hong]'s Articles
[Zhang, Bo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Luo, Junru]'s Articles
[Qiao, Hong]'s Articles
[Zhang, Bo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.