Openly accessible

Learning robust low-rank approximation for crowdsourcing on Riemannian Manifold

Li, Qian, Wang, Zhichao, Li, Gang, Cao, Yanan, Xiong, Gang and Guo, Li 2017, Learning robust low-rank approximation for crowdsourcing on Riemannian Manifold, in ICCS 2017 : Proceedings of the International Conference on Computational Science, Zurich, Switzerland, Elsevier, Amsterdam, The Netherlands, pp. 285-294, doi: 10.1016/j.procs.2017.05.179.

Attached Files
Name Description MIMEType Size Downloads
gang-learningrobust-2017.pdf Published version application/pdf 628.97KB 1

Title Learning robust low-rank approximation for crowdsourcing on Riemannian Manifold
Author(s) Li, Qian
Wang, Zhichao
Li, GangORCID iD for Li, Gang orcid.org/0000-0003-1583-641X
Cao, Yanan
Xiong, Gang
Guo, Li
Conference name Computational Science. Conference (2017 : Zurich, Switzerland)
Conference location Zurich, Switzerland
Conference dates 2017/06/12 - 2017/06/14
Title of proceedings ICCS 2017 : Proceedings of the International Conference on Computational Science, Zurich, Switzerland
Editor(s) Koumoutsakos, P
Lees, M
Krzhizhanovskaya, V
Dongarra, J
Sloot, P
Publication date 2017
Start page 285
End page 294
Total pages 10
Publisher Elsevier
Place of publication Amsterdam, The Netherlands
Keyword(s) Crowdsourcing
Low-Rank
Riemannian Optimization
Summary Recently, crowdsourcing has attracted substantial research interest due to its efficiency in collecting labels for machine learning and computer vision tasks. This paper proposes a Rieman-nian manifold optimization algorithm, ROLA (Robust Low-rank Approximation), to aggregate the labels from a novel perspective. Specifically, a novel low-rank approximation model is proposed to capture underlying correlation among annotators meanwhile identify annotator-specific noise. More significantly, ROLA defines the label noise in crowdsourcing as annotator-specific noise, which can be well regularized by l2,1-norm. The proposed ROLA can improve the aggregation performance when compared with state-of-the-art crowdsourcing methods.
Notes These proceeding where published in Procedia Computer Science, v.108, 2017
ISSN 1877-0509
Language eng
DOI 10.1016/j.procs.2017.05.179
Field of Research 08 Information And Computing Sciences
10 Technology
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2017, The Authors
Free to Read? Yes
Use Rights Creative Commons Attribution Non-Commercial No-Derivatives licence
Persistent URL http://hdl.handle.net/10536/DRO/DU:30105046

Document type: Conference Paper
Collections: School of Information Technology
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 18 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Thu, 23 Nov 2017, 18:58:26 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.