中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Adaptively sharing multi-levels of distributed representations in multi-task learning

文献类型：期刊论文

作者Wang, Tianxin4,5; Zhuang, Fuzhen2,6; Sun, Ying4,5; Zhang, Xiangliang3; Lin, Leyu1; Xia, Feng1; He, Lei1; He, Qing4,5
刊名INFORMATION SCIENCES
出版日期2022-04-01
卷号591页码:226-234
关键词Multi-task learning Deep learning Machine learning
ISSN号0020-0255
DOI10.1016/j.ins.2022.01.035
英文摘要In multi-task learning, the performance is often sensitive to the relationships between tasks. Thus it is important to study how to exploit the complex relationships across different tasks. One line of research captures the complex task relationships, by increasing the model capacity and thus requiring a large training dataset. However in many real-world applications, the amount of labeled data is limited. In this paper, we propose a light weight and specially designed architecture, which aims to model task relationships for small or middle-sized datasets. The proposed framework learns a task-specific ensemble of subnetworks in different depths, and is able to adapt the model architecture for the given data. The task-specific ensemble parameters are learned simultaneously with the weights of the network by optimizing a single loss function defined with respect to the end task. The hierarchical model structure is able to share both general and specific distributed representations to capture the inherent relationships between tasks. We validate our approach on various types of tasks, including synthetic task, article recommendation task and vision task. The results demonstrate the advantages of our model over several competitive baselines especially when the tasks are less-related.(c) 2022 Published by Elsevier Inc.
资助项目National Key Research and Development Program of China[2021ZD0113602] ; National Natural Science Foundation of China[62176014] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[U1811461]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000770687400012
出版者ELSEVIER SCIENCE INC
源URL[http://119.78.100.204/handle/2XEOYT63/18942]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhuang, Fuzhen
作者单位1.Tencent, WeChat Grp, Shenzhen, Peoples R China
2.Beihang Univ, Sch Comp Sci, SKLSDE, Beijing 100191, Peoples R China
3.Univ Notre Dame, Comp Sci & Engn, Notre Dame, IN 46556 USA
4.Chinese Acad Sci, CAS, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
6.Beihang Univ, Inst Artificial Intelligence, Beijing 100191, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Tianxin,Zhuang, Fuzhen,Sun, Ying,et al. Adaptively sharing multi-levels of distributed representations in multi-task learning[J]. INFORMATION SCIENCES,2022,591:226-234.
APA Wang, Tianxin.,Zhuang, Fuzhen.,Sun, Ying.,Zhang, Xiangliang.,Lin, Leyu.,...&He, Qing.(2022).Adaptively sharing multi-levels of distributed representations in multi-task learning.INFORMATION SCIENCES,591,226-234.
MLA Wang, Tianxin,et al."Adaptively sharing multi-levels of distributed representations in multi-task learning".INFORMATION SCIENCES 591(2022):226-234.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。