Active learning in multiple-class classification problems via individualized binary models

We propose a unified algorithm for both categorical and ordinal labeled data in multiclass classification problems, where each subject belongs to one class only. In training an effective classification rule, it is critical that one have and rely on a sufficient amount of reliably labeled data. As in...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computational statistics & data analysis Ročník 145; s. 106911
Hlavní autori: Li, Jingjing, Chen, Zimu, Wang, Zhanfeng, Chang, Yuan-chin Ivan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.05.2020
Predmet:
A-optimality design
algorithms
experimental design
Individualized binary estimation
learning
Multiple-class classification
sample size
Sequential estimation
Stopping time
Multiple-class classification
Stopping time
Sequential estimation
Individualized binary estimation
A-optimality design
ISSN:0167-9473, 1872-7352
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We propose a unified algorithm for both categorical and ordinal labeled data in multiclass classification problems, where each subject belongs to one class only. In training an effective classification rule, it is critical that one have and rely on a sufficient amount of reliably labeled data. As information on the training sample sizes needed to obtain satisfactory performance is lacking, we adopt an adaptive subject recruiting scheme with an experimental design criterion to shorten the training process. Because this kind of active learning method is naturally conducted in a sequential manner, we adopt sequential analysis to control the required sample size and ensure the performance of the final classifier. Additionally, we report its statistical properties and numerical results from using synthesized and real data.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0167-9473
1872-7352
DOI:10.1016/j.csda.2020.106911