SIA OpenIR  > 机器人学研究室
Representative Task Self-Selection for Flexible Clustered Lifelong Learning
Sun G(孙干)1,2; Cong Y(丛杨)2; Wang QQ(王倩倩)3; Zhong BN(钟必能)4; Fu Y(付昀)1,5
Department机器人学研究室
Source PublicationIEEE Transactions on Neural Networks and Learning Systems
ISSN2162-237X
2021
Pages1-15
Indexed ByEI
EI Accession number20210209735344
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China under Grant 61722311, Grant U1613214, Grant 61821005, and Grant 62003336 ; National Postdoctoral Innovative Talents Support Program under Grant BX20200353 ; National Nature Science Foundation of China under Grant 61533015
KeywordClustering analysis lifelong machine learning multitask learning (MTL) transfer learning
Abstract

Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are of prescribed size and can degenerate the performance for both learned tasks and coming ones when facing with a new task environment (cluster). To address this challenge, we propose a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL). Specifically, the feature learning library modeled by an autoencoder architecture maintains a set of representation common across all the observed tasks, and the model knowledge library can be self-selected by identifying and adding new representative models (clusters). When a new task arrives, our FCL model firstly transfers knowledge from these libraries to encode the new task, i.e., effectively and selectively soft-assigning this new task to multiple representative models over feature learning library. Then: 1) the new task with a higher outlier probability will be judged as a new representative, and used to redefine both feature learning library and representative models over time; or 2) the new task with lower outlier probability will only refine the feature learning library. For model optimization, we cast this lifelong learning problem as an alternating direction minimization problem as a new task comes. Finally, we evaluate the proposed framework by analyzing several multitask data sets, and the experimental results demonstrate that our FCL model can achieve better performance than most lifelong learning frameworks, even batch clustered multitask learning models.

Language英语
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28138
Collection机器人学研究室
Corresponding AuthorSun G(孙干)
Affiliation1.Department of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115 USA
2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
3.Xidian University, Xian, Shanxi 710071, China.
4.Department of Computer Science, Guangxi Normal University, Guilin 541004, China.
5.Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115 USA.
Recommended Citation
GB/T 7714
Sun G,Cong Y,Wang QQ,et al. Representative Task Self-Selection for Flexible Clustered Lifelong Learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2021:1-15.
APA Sun G,Cong Y,Wang QQ,Zhong BN,&Fu Y.(2021).Representative Task Self-Selection for Flexible Clustered Lifelong Learning.IEEE Transactions on Neural Networks and Learning Systems,1-15.
MLA Sun G,et al."Representative Task Self-Selection for Flexible Clustered Lifelong Learning".IEEE Transactions on Neural Networks and Learning Systems (2021):1-15.
Files in This Item:
File Name/Size DocType Version Access License
Representative Task (4768KB)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
[Wang QQ(王倩倩)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Wang QQ(王倩倩)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Wang QQ(王倩倩)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Representative Task Self-Selection for Flexible Clustered Lifelong Learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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