Less annotation on active learning using confidence-weighted predictions

doi:10.1016/j.neucom.2017.10.004

	Less annotation on active learning using confidence-weighted predictions
	Yang, Xiaodong 1,2,3,4; Chen, Yiqiang 1,2,3,4; Yu, Hanchao 1,3,4; Zhang, Yingwei 1,2,3,4
	2018-01-31
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	275 页码:1629-1636
摘要	This paper proposes an efficient and effective active online sequential learning approach, named as Less Annotated Active Learning Extreme Learning Machine (LAAL-ELM). It leverages the predictions' confidence of the new arriving data to actively select both query-annotated samples and confidence-weighted predict-annotated ones to update the classifier, which contributes to less actively query annotation, and applies WOS-ELM, a discriminant model, to significantly reduce the computation complexity for doing online updating in one step. The proposed approach firstly gives a principle to evaluate confidence of the prediction in WOS-ELM; then determines what and how to update the model with new arriving data in the online phase: the uncertain instances are annotated by query their classes, almost-certain ones are weighted on its prediction's confidence and the certain ones are discarded directly for reducing over-fitting; at last, the weighted and query-annotated samples are used to update the classifier. The proposed approach is evaluated on five real-world benchmark classification issues. And the experimental results demonstrate that the proposed LAAL-ELM can effectively reduce the number of queried samples while maintaining high level of classification performance. (c) 2017 Elsevier B.V. All rights reserved.
关键词	Extreme Learning Machine Online sequential learning Active learning Less annotation
DOI	10.1016/j.neucom.2017.10.004
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[61502456] ; Natural Science Foundation of China[61572471] ; Science and Technology Planning Project of Guangdong Province, China[2015B010105001] ; Beijing Municipal Science & Technology Commission[Z161100000216140] ; Beijing Municipal Science & Technology Commission[Z171100000117013]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000418370200153
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/6279
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 4.Beijing Key Lab Parkinsons Dis, Beijing 100053, Peoples R China
推荐引用方式 GB/T 7714	Yang, Xiaodong,Chen, Yiqiang,Yu, Hanchao,et al. Less annotation on active learning using confidence-weighted predictions[J]. NEUROCOMPUTING,2018,275:1629-1636.
APA	Yang, Xiaodong,Chen, Yiqiang,Yu, Hanchao,&Zhang, Yingwei.(2018).Less annotation on active learning using confidence-weighted predictions.NEUROCOMPUTING,275,1629-1636.
MLA	Yang, Xiaodong,et al."Less annotation on active learning using confidence-weighted predictions".NEUROCOMPUTING 275(2018):1629-1636.