SIA OpenIR  > 机器人学研究室
Clustered Lifelong Learning via Representative Task Selection
Sun G(孙干)1,2,3; Cong Y(丛杨)1,2; Kong, Yu4; Xu XW(徐晓伟)5
Department机器人学研究室
Conference Name2018 IEEE International Conference on Big Knowledge (ICBK)
Conference DateNovember 17-18, 2018
Conference PlaceSingapore
Source Publication2018 IEEE International Conference on Big Knowledge (ICBK)
PublisherIEEE
Publication PlaceNew York
2018
Pages1248-1253
Indexed ByEI ; CPCI(ISTP)
EI Accession number20190706506420
WOS IDWOS:000464691700153
Contribution Rank1
ISBN978-1-5386-9159-5
KeywordLifelong Learning Clustering Analysis Multi-task Learning Transfer Learning
AbstractConsider the lifelong machine learning problem where the objective is to learn new consecutive tasks depending on previously accumulated experiences, i.e., knowledge library. In comparison with most state-of-the-arts which adopt knowledge library with prescribed size, in this paper, we propose a new incremental clustered lifelong learning model with two libraries: feature library and model library, called Clustered Lifelong Learning (CL3), in which the feature library maintains a set of learned features common across all the encountered tasks, and the model library is learned by identifying and adding representative models (clusters). When a new task arrives, the original task model can be firstly reconstructed by representative models measured by capped `2-norm distance, i.e., effectively assigning the new task model to multiple representative models under feature library. Based on this assignment knowledge of new task, the objective of our CL3 model is to transfer the knowledge from both feature library and model library to learn the new task. The new task 1) with a higher outlier probability will then be judged as a new representative, and used to refine both feature library and representative models over time; 2) with lower outlier probability will only update the feature library. For the model optimisation, we cast this problem as an alternating direction minimization problem. To this end, the performance of CL3 is evaluated through comparing with most lifelong learning models, even some batch clustered multi-task learning models.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/23846
Collection机器人学研究室
Corresponding AuthorCong Y(丛杨)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China
3.University of Chinese Academy of Sciences, Beijing, China
4.College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, USA
5.Department of Information Science, University of Arkansas at Little Rock, Little Rock, USA
Recommended Citation
GB/T 7714
Sun G,Cong Y,Kong, Yu,et al. Clustered Lifelong Learning via Representative Task Selection[C]. New York:IEEE,2018:1248-1253.
Files in This Item: Download All
File Name/Size DocType Version Access License
Clustered Lifelong L(581KB)会议论文 开放获取CC BY-NC-SAView Download
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
[Kong, Yu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Kong, Yu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun G(孙干)]'s Articles
[Cong Y(丛杨)]'s Articles
[Kong, Yu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Clustered Lifelong Learning via Representative Task Selection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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