UM
Residential Collegefalse
Status即將出版Forthcoming
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
Li, Xingjian1,2; Xiong, Haoyi1,2; An, Haozhe1; Xu, Chengzhong2; Dou, Dejing1
2022
Source PublicationNeural Processing Letters
ISSN1370-4621
Abstract

Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks. While such a practice has been studied as a way to leverage “privileged information” about the distribution of the data, a well-trained learner with soft classification outputs should be first obtained as a prior to generate such privileged information. To solve such a “chicken-and-egg” problem, we propose COLAM framework that Co-Learns DNNs and soft labels through Alternating Minimization of two objectives—(a) the training loss subject to soft labels and (b) the objective to learn improved soft labels—in one end-to-end training procedure. We performed extensive experiments to compare our proposed method with a series of baselines. The experiment results show that COLAM achieves improved performance on many tasks with better testing classification accuracy. We also provide both qualitative and quantitative analyses that explain why COLAM works well.

KeywordDeep Learning Neural Networks Soft Label
DOI10.1007/s11063-022-10830-9
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000795184900001
Scopus ID2-s2.0-85132635785
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Affiliation1.Big Data Lab, Baidu Research, Beijing, China
2.University of Macau, Zhuhai, China
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Li, Xingjian,Xiong, Haoyi,An, Haozhe,et al. COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization[J]. Neural Processing Letters,2022.
APA Li, Xingjian,Xiong, Haoyi,An, Haozhe,Xu, Chengzhong,&Dou, Dejing.(2022).COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization.Neural Processing Letters.
MLA Li, Xingjian,et al."COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization".Neural Processing Letters (2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Xingjian]'s Articles
[Xiong, Haoyi]'s Articles
[An, Haozhe]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Xingjian]'s Articles
[Xiong, Haoyi]'s Articles
[An, Haozhe]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Xingjian]'s Articles
[Xiong, Haoyi]'s Articles
[An, Haozhe]'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.