中文版 | English
Title

Learning Linear and Nonlinear Low-Rank Structure in Multi-Task Learning

Author
Publication Years
2022
DOI
Source Title
ISSN
1041-4347
EISSN
1558-2191
VolumePPIssue:99Pages:1-12
Abstract

As the trace norm can discover low-rank structures in a matrix, it has been widely used in multi-task learning to recover the low-rank structure contained in the parameter matrix. Recently, with the emerging of big complex datasets and the popularity of deep learning techniques, tensor trace norms have been used for deep multi-task models. However, existing tensor trace norms exhibit some limitations. For example, they cannot discover all the low-rank structures in a tensor, they require users to manually specify the importance of each component in the corresponding tensor trace norm, and they only capture the linear low-rank structure. To solve the first issue, in this paper, we propose a Generalized Tensor Trace Norm (GTTN). The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures. For the second issue, in the induced objective function with the GTTN, we propose four strategies to learn combination coefficients in the GTTN. Furthermore, we propose the Nonlinear GTTN (NGTTN) to capture nonlinear low-rank structure among all the tasks. Experiments on benchmark datasets demonstrate the effectiveness of the proposed GTTN and NGTTN.

Keywords
URL[Source Record]
Indexed By
SCI ; EI
Language
English
SUSTech Authorship
First
EI Accession Number
20223812754010
EI Keywords
Deep Learning ; Job Analysis ; Matrix Algebra ; Neural Networks
ESI Classification Code
Ergonomics And Human Factors Engineering:461.4 ; Algebra:921.1
ESI Research Field
ENGINEERING
Scopus EID
2-s2.0-85137905337
Data Source
Scopus
PDF urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9875058
Citation statistics
Cited Times [WOS]:0
Document TypeJournal Article
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/402402
DepartmentDepartment of Computer Science and Engineering
工学院_斯发基斯可信自主研究院
Affiliation
1.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, China
2.Department of Computer Science and Engineering and Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, China
3.National Key Laboratory for Novel Software Technology, Nanjing University, China
First Author AffilicationDepartment of Computer Science and Engineering
First Author's First AffilicationDepartment of Computer Science and Engineering
Recommended Citation
GB/T 7714
Zhang,Yi,Zhang,Yu,Wang,Wei. Learning Linear and Nonlinear Low-Rank Structure in Multi-Task Learning[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2022,PP(99):1-12.
APA
Zhang,Yi,Zhang,Yu,&Wang,Wei.(2022).Learning Linear and Nonlinear Low-Rank Structure in Multi-Task Learning.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,PP(99),1-12.
MLA
Zhang,Yi,et al."Learning Linear and Nonlinear Low-Rank Structure in Multi-Task Learning".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING PP.99(2022):1-12.
Files in This Item:
There are no files associated with this item.
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Zhang,Yi]'s Articles
[Zhang,Yu]'s Articles
[Wang,Wei]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Zhang,Yi]'s Articles
[Zhang,Yu]'s Articles
[Wang,Wei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang,Yi]'s Articles
[Zhang,Yu]'s Articles
[Wang,Wei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

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