PSYCH OpenIR  > 中国科学院行为科学重点实验室
Feature-Based Transfer Learning Based on Distribution Similarity
Zhong, Xiaofeng1; Guo, Shize2; Shan, Hong1; Gao, Liang2; Xue, Di3; Zhao, Nan4
First AuthorZhong, Xiaofeng
Source PublicationIEEE Access
Contribution Rank4

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.

KeywordDistribution Similarity Feature Transfer Kl Divergence Transfer Learning
Subject AreaLabeling - Learning Systems - Personnel Training - Social Networking (Online)
MOST Discipline CatalogueProbability Distributions
Indexed BySCIE ; EI
Project Intro.

This work was supported by the Scientific Research Funds of PLA under Grant AWS13J003.

PublisherInstitute of Electrical and Electronics Engineers Inc.
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Corresponding AuthorZhong, Xiaofeng
Affiliation1.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
Recommended Citation
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.
Files in This Item:
File Name/Size DocType Version Access License
Feature-Based Transf(5378KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhong, Xiaofeng]'s Articles
[Guo, Shize]'s Articles
[Shan, Hong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhong, Xiaofeng]'s Articles
[Guo, Shize]'s Articles
[Shan, Hong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhong, Xiaofeng]'s Articles
[Guo, Shize]'s Articles
[Shan, Hong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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