Presentation 2013-07-18
Online learning from Crowds
Tran QUANG KHAI, Jun SAKUMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In our paper, we propose an online learning algorithm for classification problems using crowdsourcing services. By using the online learning approach, we are able to solve the problem that the existed method couldn't deal with when the reliability of workers and the tend of tasks change over time. We show that under this learning condition the prediction accuracy of the existed method will be decreased. And using online learning method to solve online the existed method, the batch learning, we are able to solve this problem. After defining a new regret for online in crowdsourcing, we use it to estimate our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) crowdsourcing / online learning / regret / logistic regression
Paper # IBISML2013-4
Date of Issue

Conference Information
Committee IBISML
Conference Date 2013/7/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Online learning from Crowds
Sub Title (in English)
Keyword(1) crowdsourcing
Keyword(2) online learning
Keyword(3) regret
Keyword(4) logistic regression
1st Author's Name Tran QUANG KHAI
1st Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Jun SAKUMA
2nd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba
Date 2013-07-18
Paper # IBISML2013-4
Volume (vol) vol.113
Number (no) 139
Page pp.pp.-
#Pages 8
Date of Issue