Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective

doi:10.1109/TKDE.2009.205

	Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective
	Zhuang, Fuzhen 1; Luo, Ping ; Xiong, Hui 2; Xiong, Yuhong ; He, Qing 1; Shi, Zhongzhi 1
	2010-12-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	22 期号:12 页码:1664-1678
摘要	Classification across different domains studies how to adapt a learning model from one domain to another domain which shares similar data characteristics. While there are a number of existing works along this line, many of them are only focused on learning from a single source domain to a target domain. In particular, a remaining challenge is how to apply the knowledge learned from multiple source domains to a target domain. Indeed, data from multiple source domains can be semantically related, but have different data distributions. It is not clear how to exploit the distribution differences among multiple source domains to boost the learning performance in a target domain. To that end, in this paper, we propose a consensus regularization framework for learning from multiple source domains to a target domain. In this framework, a local classifier is trained by considering both local data available in one source domain and the prediction consensus with the classifiers learned from other source domains. Moreover, we provide a theoretical analysis as well as an empirical study of the proposed consensus regularization framework. The experimental results on text categorization and image classification problems show the effectiveness of this consensus regularization learning method. Finally, to deal with the situation that the multiple source domains are geographically distributed, we also develop the distributed version of the proposed algorithm, which avoids the need to upload all the data to a centralized location and helps to mitigate privacy concerns.
关键词	Classification multiple source domains cross-domain learning consensus regularization
DOI	10.1109/TKDE.2009.205
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[60675010] ; National Science Foundation of China[60933004] ; National Science Foundation of China[60975039] ; 863 National High-Tech Program[2007AA01Z132] ; National Basic Research Priorities Programme[2007CB311004] ; National Science and Technology Support Plan[2006BAC08B06] ; US National Science Foundation (NSF)[CNS 0831186] ; Rutgers Seed Funding for Collaborative Computing Research
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:000283133800002
出版者	IEEE COMPUTER SOC
引用统计	被引频次：47[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/2XEOYT63/12273
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhuang, Fuzhen
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Rutgers State Univ, Management Sci & Informat Syst Dept, Rutgers Business Sch Newark & New Brunswick, Newark, NJ 07102 USA
推荐引用方式 GB/T 7714	Zhuang, Fuzhen,Luo, Ping,Xiong, Hui,et al. Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2010,22(12):1664-1678.
APA	Zhuang, Fuzhen,Luo, Ping,Xiong, Hui,Xiong, Yuhong,He, Qing,&Shi, Zhongzhi.(2010).Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,22(12),1664-1678.
MLA	Zhuang, Fuzhen,et al."Cross-Domain Learning from Multiple Sources: A Consensus Regularization Perspective".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 22.12(2010):1664-1678.