SIA OpenIR  > 机器人学研究室
Continual Multiview Task Learning via Deep Matrix Factorization
Sun G(孙干)1,2; Cong Y(丛杨)2; Zhang, Yulun1; Zhao GS(赵国帅)3; Fu Y(付昀)1,4
Department机器人学研究室
Source PublicationIEEE Transactions on Neural Networks and Learning Systems
ISSN2162-237X
2021
Volume32Issue:1Pages:139-150
Indexed ByEI
EI Accession number20210309770182
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China under Grant 61722311, Grant U1613214, and Grant 61821005
KeywordDeep matrix factorization lifelong machine learning multiview learning sparse subspace learning
Abstract

The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.

Language英语
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28160
Collection机器人学研究室
Corresponding AuthorSun G(孙干)
Affiliation1.Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, United States
2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
3.School of Software Engineering, Xi'an Jiaotong University, Xi'an, China
4.Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115 USA
Recommended Citation
GB/T 7714
Sun G,Cong Y,Zhang, Yulun,et al. Continual Multiview Task Learning via Deep Matrix Factorization[J]. IEEE Transactions on Neural Networks and Learning Systems,2021,32(1):139-150.
APA Sun G,Cong Y,Zhang, Yulun,Zhao GS,&Fu Y.(2021).Continual Multiview Task Learning via Deep Matrix Factorization.IEEE Transactions on Neural Networks and Learning Systems,32(1),139-150.
MLA Sun G,et al."Continual Multiview Task Learning via Deep Matrix Factorization".IEEE Transactions on Neural Networks and Learning Systems 32.1(2021):139-150.
Files in This Item:
File Name/Size DocType Version Access License
Continual Multiview (2443KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Zhang, Yulun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Zhang, Yulun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Zhang, Yulun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Continual Multiview Task Learning via Deep Matrix Factorization.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.