MaxMatch: Semi-Supervised Learning With Worst-Case Consistency

doi:10.1109/TPAMI.2022.3208419

	MaxMatch: Semi-Supervised Learning With Worst-Case Consistency
	Jiang, Yangbangyan 1,2; Li, Xiaodan 3; Chen, Yuefeng 3; He, Yuan 3; Xu, Qianqian 4; Yang, Zhiyong 5; Cao, Xiaochun 6; Huang, Qingming 4,5,7,8
	2023-05-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	45 期号:5 页码:5970-5987
摘要	In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-art models are based on the idea of pursuing consistent model predictions over unlabeled data toward the input noise, which is called consistency regularization. Nonetheless, there is a lack of theoretical insights into the reason behind its success. To bridge the gap between theoretical and practical results, we propose a worst-case consistency regularization technique for SSL in this article. Specifically, we first present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants. We then provide a simple but effective algorithm to solve the proposed minimax problem, and theoretically prove that it converges to a stationary point. Experiments on five popular benchmark datasets validate the effectiveness of our proposed method.
关键词	Predictive models Training Data models Semantics Perturbation methods Computational modeling Benchmark testing Semi-supervised learning consistency regularization worst-case consistency image classification
DOI	10.1109/TPAMI.2022.3208419
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[62025604] ; National Natural Science Foundation of China[U1936208] ; National Natural Science Foundation of China[6212200758] ; National Natural Science Foundation of China[61976202] ; Fundamental Research Funds for the Central Universities ; Youth Innovation Promotion Association CAS ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB28000000] ; China National Postdoctoral Program for Innovative Talents[BX2021298] ; China Postdoctoral Science Foundation[2022M713101]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000964792800040
出版者	IEEE COMPUTER SOC
引用统计	被引频次：11[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/2XEOYT63/21398
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xu, Qianqian; Huang, Qingming
作者单位	1.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China 2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China 3.Alibaba Grp, Secur Dept, Hangzhou 311121, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 6.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen Campus, Shenzhen 518107, Peoples R China 7.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management BDKM, Beijing 101408, Peoples R China 8.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Yangbangyan,Li, Xiaodan,Chen, Yuefeng,et al. MaxMatch: Semi-Supervised Learning With Worst-Case Consistency[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(5):5970-5987.
APA	Jiang, Yangbangyan.,Li, Xiaodan.,Chen, Yuefeng.,He, Yuan.,Xu, Qianqian.,...&Huang, Qingming.(2023).MaxMatch: Semi-Supervised Learning With Worst-Case Consistency.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(5),5970-5987.
MLA	Jiang, Yangbangyan,et al."MaxMatch: Semi-Supervised Learning With Worst-Case Consistency".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.5(2023):5970-5987.