Robust Lifelong Multi-task Multi-view Representation Learning

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

	Robust Lifelong Multi-task Multi-view Representation Learning
	Sun G(孙干)1,2,3; Cong Y(丛杨)1,2; Li, Jun 4; Fu Y(付昀)4
	2018
会议日期	November 17-18, 2018
会议地点	Singapore
关键词	Lifelong machine learning Multi-view learning Multi-task Learning Online learning
页码	91-98
英文摘要	The state-of-the-art multi-task multi-view learning (MTMV) tackles the learning scenario where multiple tasks are associated with each other via multiple shared feature views. However, in online practical scenarios where the learning tasks have heterogeneous features collected from multiple views, e.g., multiple sources, the state-of-the-arts with single view cannot work well. To tackle this issue, in this paper, we propose a Robust Lifelong Multi-task Multi-view Representation Learning (rLM2L) model to accumulate the knowledge from online multi-view tasks. More specifically, we firstly design a set of view-specific libraries to maintain the intra-view correlation information of each view, and further impose an orthogonal promoting term to enforce libraries to be as independent as possible. When online new multiview task is coming, rLM2L model decomposes all views of the new task into a common view-invariant space by transferring the knowledge of corresponding library. In this view-invariant space, capturing underlying inter-view correlation and identifying taskspecific views for the new task are jointly employed via a robust multi-task learning formulation. Then the view-specific libraries can be refined over time to keep on improving across all tasks. For the model optimization, the proximal alternating linearized minimization algorithm is adopted to optimize our nonconvex model alternatively to achieve lifelong learning. Finally, extensive experiments on benchmark datasets shows that our proposed rLM2L model outperforms existing lifelong learning models, while it can discover task-specific views from sequential multi-view task with less computational burden.
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	978-1-5386-9125-0
WOS记录号	WOS:000468072300012
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/23858]
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.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation 3.University of Chinese Academy of Sciences, Beijing, China 4.Department of Electrical and Computer Engineering, Northeastern University, USA
推荐引用方式 GB/T 7714	Sun G,Cong Y,Li, Jun,et al. Robust Lifelong Multi-task Multi-view Representation Learning[C]. 见:. Singapore. November 17-18, 2018.