Softly Associative Transfer Learning for Cross-Domain Classification

doi:10.1109/TCYB.2019.2891577

	Softly Associative Transfer Learning for Cross-Domain Classification
	Wang, Deqing 1; Lu, Chenwei 1; Wu, Junjie 2,3,4; Liu, Hongfu 5; Zhang, Wenjie 6; Zhuang, Fuzhen 7,8; Zhang, Hui 1
	2020-11-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	50 期号:11 页码:4709-4721
摘要	The main challenge of cross-domain text classification is to train a classifier in a source domain while applying it to a different target domain. Many transfer learning-based algorithms, for example, dual transfer learning, triplex transfer learning, etc., have been proposed for cross-domain classification, by detecting a shared low-dimensional feature representation for both source and target domains. These methods, however, often assume that the word clusters matrix or the clusters association matrix as knowledge transferring bridges are exactly the same across different domains, which is actually unrealistic in real-world applications and, therefore, could degrade classification performance. In light of this, in this paper, we propose a softly associative transfer learning algorithm for cross-domain text classification. Specifically, we integrate two non-negative matrix tri-factorizations into a joint optimization framework, with approximate constraints on both word clusters matrices and clusters association matrices so as to allow proper diversity in knowledge transfer, and with another approximate constraint on class labels in source domains in order to handle noisy labels. An iterative algorithm is then proposed to solve the above problem, with its convergence verified theoretically and empirically. Extensive experimental results on various text datasets demonstrate the effectiveness of our algorithm, even with the presence of abundant state-of-the-art competitors.
关键词	Task analysis Knowledge transfer Matrix decomposition Bridges Optimization Data models Feature extraction Cross-domain text classification non-negative matrix tri-factorizations (NMTFs) softly associative transfer learning (sa-TL)
DOI	10.1109/TCYB.2019.2891577
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[71501003] ; National Natural Science Foundation of China[71725002] ; National Natural Science Foundation of China[71531001] ; National Natural Science Foundation of China[U1636210] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[61773361] ; State Key Laboratory of Software Development Environment[SKLSDE-2018ZX-13]
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000583709500013
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：25[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/2XEOYT63/16101
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wu, Junjie
作者单位	1.Beihang Univ, Sch Comp Sci, Beijing 100191, Peoples R China 2.Beihang Univ, Sch Econ & Management, Beijing 100191, Peoples R China 3.Beihang Univ, Beijing Adv Innovat Ctr Big Data & Brain Comp, Beijing 100191, Peoples R China 4.Beihang Univ, Beijing Key Lab Emergency Support Simulat Technol, Beijing 100191, Peoples R China 5.Brandeis Univ, Sch Comp Sci, Waltham, MA 02453 USA 6.Yidian News Inc, Ctr Dev & Res, Beijing, Peoples R China 7.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 8.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Deqing,Lu, Chenwei,Wu, Junjie,et al. Softly Associative Transfer Learning for Cross-Domain Classification[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(11):4709-4721.
APA	Wang, Deqing.,Lu, Chenwei.,Wu, Junjie.,Liu, Hongfu.,Zhang, Wenjie.,...&Zhang, Hui.(2020).Softly Associative Transfer Learning for Cross-Domain Classification.IEEE TRANSACTIONS ON CYBERNETICS,50(11),4709-4721.
MLA	Wang, Deqing,et al."Softly Associative Transfer Learning for Cross-Domain Classification".IEEE TRANSACTIONS ON CYBERNETICS 50.11(2020):4709-4721.