A parameter-free self-training algorithm based on the three successive confirmation rule

doi:10.1016/j.engappai.2025.110165

	A parameter-free self-training algorithm based on the three successive confirmation rule
	Wang, Jikui1 ; Zhao, Wei 1; Shang, Qingsheng1 ; Nie, Feiping2
	2025-03-15
在线发表日期	2025-02
发表期刊	ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
卷号	144
摘要	Semi-supervised learning is a popular research topic today, and self-training is a classical semi-supervised learning framework. How to select high-confidence samples in self-training is a critical step. However, the existing algorithms do not consider both global and local information of the data. In the paper, we propose a parameter-free self-training algorithm based on the three successive confirmation rule, which integrates global and local information to identify high-confidence samples. Concretely, the local information is obtained by using k nearest neighbors and global information is derived from the three successive confirmation rule. This dual selection strategy helps to improve the quality of high-confidence samples and further improve the performance of classification. We conduct experiments on 14 benchmark datasets, comparing our method with other self-training algorithms. We use accuracy and F-score as performance metrics. The experimental results demonstrate that our algorithm significantly improves classification performance, proving its effectiveness and superiority in semi-supervised learning.
关键词	Semi-supervised learning Self-training algorithm High-confidence samples Three successive confirmation rule
DOI	10.1016/j.engappai.2025.110165
收录类别	SCIE ; EI
ISSN	0952-1976
语种	英语
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Multidisciplinary ; Engineering, Electrical & Electronic
WOS记录号	WOS:001417146900001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
EI入藏号	20250517798970
EI主题词	Self-supervised learning
EI分类号	1101.2 Machine Learning ; 1101.2.1 Deep Learning ; 1103.3 Data Communication, Equipment and Techniques ; 1105.3 Blockchain Technology
原始文献类型	Article
EISSN	1873-6769
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/38740
专题	信息工程与人工智能学院长青学院
通讯作者	Wang, Jikui
作者单位	1.Lanzhou Univ Finance & Econ, Coll Informat Engn & Artificial Intelligence, Lanzhou 730020, Gansu, Peoples R China; 2.Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN, Xian 710072, Shaanxi, Peoples R China
第一作者单位	兰州财经大学
通讯作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Wang, Jikui,Zhao, Wei,Shang, Qingsheng,et al. A parameter-free self-training algorithm based on the three successive confirmation rule[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2025,144.
APA	Wang, Jikui,Zhao, Wei,Shang, Qingsheng,&Nie, Feiping.(2025).A parameter-free self-training algorithm based on the three successive confirmation rule.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,144.
MLA	Wang, Jikui,et al."A parameter-free self-training algorithm based on the three successive confirmation rule".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 144(2025).