Item Response Theory Based Ensemble in Machine Learning

doi:10.1007/s11633-020-1239-y

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Item Response Theory Based Ensemble in Machine Learning
	Ziheng Chen; Hongshik Ahn
发表期刊	International Journal of Automation and Computing
ISSN	1476-8186
	2020
卷号	17 期号:5 页码:621-636
摘要	In this article, we propose a novel probabilistic framework to improve the accuracy of a weighted majority voting algorithm. In order to assign higher weights to the classifiers which can correctly classify hard-to-classify instances, we introduce the item response theory (IRT) framework to evaluate the samples′ difficulty and classifiers′ ability simultaneously. We assigned the weights to classifiers based on their abilities. Three models are created with different assumptions suitable for different cases. When making an inference, we keep a balance between the accuracy and complexity. In our experiment, all the base models are constructed by single trees via bootstrap. To explain the models, we illustrate how the IRT ensemble model constructs the classifying boundary. We also compare their performance with other widely used methods and show that our model performs well on 19 datasets.
关键词	Classification ensemble learning item response theory machine learning expectation maximization (EM) algorithm.
DOI	10.1007/s11633-020-1239-y
引用统计	被引频次：22[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42263
专题	学术期刊_Machine Intelligence Research
作者单位	Department of Applied Mathematics and Statistics, Stony Brook University, New York 11794−3600, USA
推荐引用方式 GB/T 7714	Ziheng Chen,Hongshik Ahn. Item Response Theory Based Ensemble in Machine Learning[J]. International Journal of Automation and Computing,2020,17(5):621-636.
APA	Ziheng Chen,&Hongshik Ahn.(2020).Item Response Theory Based Ensemble in Machine Learning.International Journal of Automation and Computing,17(5),621-636.
MLA	Ziheng Chen,et al."Item Response Theory Based Ensemble in Machine Learning".International Journal of Automation and Computing 17.5(2020):621-636.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
IJAC-2020-02-029.pdf（1163KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载