中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Softly Associative Transfer Learning for Cross-Domain Classification

文献类型：期刊论文

作者Wang, Deqing1; Lu, Chenwei1; Wu, Junjie2,3,4; Liu, Hongfu5; Zhang, Wenjie6; Zhuang, Fuzhen7,8; Zhang, Hui1
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2020-11-01
卷号50期号:11页码:4709-4721
ISSN号2168-2267
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)
DOI10.1109/TCYB.2019.2891577
英文摘要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.
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
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000583709500013
源URL[http://119.78.100.204/handle/2XEOYT63/16100]  
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。