Clustered Lifelong Learning via Representative Task Selection

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Clustered Lifelong Learning via Representative Task Selection
	Kong, Yu 5; Sun G(孙干)2,3,4 ; Xu XW(徐晓伟)1; Cong Y(丛杨)2,3
	2018
会议日期	November 17-18, 2018
会议地点	Singapore
关键词	Lifelong Learning Clustering Analysis Multi-task Learning Transfer Learning
页码	1248-1253
英文摘要	Consider 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.
产权排序	1
会议录	2018 IEEE International Conference on Big Knowledge (ICBK)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-5386-9159-5
WOS记录号	WOS:000464691700153
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/23846]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Cong Y(丛杨)
作者单位	1.Department of Information Science, University of Arkansas at Little Rock, Little Rock, USA 2.State Key Laboratory of Robotics, Shenyang Institute of Automation 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 4.University of Chinese Academy of Sciences, Beijing, China 5.College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, USA
推荐引用方式 GB/T 7714	Kong, Yu,Sun G,Xu XW,et al. Clustered Lifelong Learning via Representative Task Selection[C]. 见:. Singapore. November 17-18, 2018.