Institutional Repository of Key Laboratory of Behavioral Science, CAS
Feature-Based Transfer Learning Based on Distribution Similarity | |
Zhong, Xiaofeng1; Guo, Shize2; Shan, Hong1; Gao, Liang2; Xue, Di3; Zhao, Nan4 | |
第一作者 | Zhong, Xiaofeng |
通讯作者邮箱 | eeijunre@126.com |
心理所单位排序 | 4 |
摘要 | Transfer learning has been found helpful at enhancing the target domain's learning process by transferring useful knowledge from other different but related source domains. In many applications, however, collecting and labeling target information is not only very difficult but also expensive. At the same time, considerable prior experience in this regard exists in other application domains. This paper proposes a feature-based transfer learning method based on distribution similarity that aims at the partial overlap of features between two domains. The non-overlapping features are completed by leveraging the distribution similarity of other features within the source domain. Features of the two domains are then reweighted in accordance with the distribution similarity between the source and target domains. This, in turn, decreases the distribution discrepancy between the two domains, therefore achieving the desired feature transfer. Results of the experiments performed on Facebook and Sina Microblog data sets demonstrate that the proposed method is capable of effectively enhancing the accuracy of the prediction function. © 2018 IEEE. |
关键词 | Distribution Similarity Feature Transfer Kl Divergence Transfer Learning |
学科领域 | Labeling - Learning Systems - Personnel Training - Social Networking (Online) |
2018-06-04 | |
语种 | 英语 |
DOI | 10.1109/ACCESS.2018.2843773 |
发表期刊 | IEEE Access |
ISSN | 2169-3536 |
卷号 | 6页码:35551-35557 |
期刊论文类型 | article |
收录类别 | SCIE ; EI |
项目简介 | This work was supported by the Scientific Research Funds of PLA under Grant AWS13J003. |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.psych.ac.cn/handle/311026/27773 |
专题 | 中国科学院行为科学重点实验室 |
通讯作者 | Zhong, Xiaofeng |
作者单位 | 1.Electronic Engineering Institute, Hefei; 230037, China; 2.Institute of North Electronic Equipment, Beijing; 100817, China; 3.College of Command Information Systems, PLA University of Science and Technology, Nanjing; 210002, China; 4.CAS Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing; 100190, China |
推荐引用方式 GB/T 7714 | Zhong, Xiaofeng,Guo, Shize,Shan, Hong,et al. Feature-Based Transfer Learning Based on Distribution Similarity[J]. IEEE Access,2018,6:35551-35557. |
APA | Zhong, Xiaofeng,Guo, Shize,Shan, Hong,Gao, Liang,Xue, Di,&Zhao, Nan.(2018).Feature-Based Transfer Learning Based on Distribution Similarity.IEEE Access,6,35551-35557. |
MLA | Zhong, Xiaofeng,et al."Feature-Based Transfer Learning Based on Distribution Similarity".IEEE Access 6(2018):35551-35557. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Feature-Based Transf(5378KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论