Smart task orderings for active online multitask learning

dc.contributor.affiliationUnitec Institute of Technologyen_NZ
dc.contributor.affiliationUniversity of Aucklanden_NZ
dc.contributor.affiliationNational Institution of Information and Communications Technology (Tokyo, Japan)en_NZ
dc.contributor.authorPang, Paul
dc.contributor.authorAn, Jianbei
dc.contributor.authorZhao, Jing
dc.contributor.authorLi, Xiaosong
dc.contributor.authorBan, Tao
dc.contributor.authorInoue, Daisuke
dc.contributor.authorSarrafzadeh, Hossein
dc.date.accessioned2015-08-12T00:51:00Z
dc.date.available2015-08-12T00:51:00Z
dc.date.issued2014-04-26
dc.description.abstractThis paper promotes active oMTL (i.e., Online Multitask Learning with task selection) by proposing two smart task ordering approaches: QR-decomposition Ordering and Minimal-loss Ordering, in which the optimal sequence of tasks for oMTL is computed as the training data/tasks are being presented. Our experimental results on four real-world datasets show that the proposed task orderings outperform all existing task ordering approaches to active oMTL.en_NZ
dc.identifier.bibliographicCitationPang, S., An, J., Zhao, J., Li, X., Ban, T., Inoue, D., and Sarrafzadeh, A. (2014). Smart Task Orderings for Active Online Multitask Learning. . Proceedings of SIAM International Conference on Data Mining(Ed.), Philadelphia, Pennysylvania, USA.en_NZ
dc.identifier.urihttps://hdl.handle.net/10652/2970
dc.language.isoenen_NZ
dc.publisherSociety for Industrial and Applied Mathematics, Activity Group on Data Mining and Analyticsen_NZ
dc.relation.urihttp://www.siam.org/meetings/sdm14/en_NZ
dc.rightsAll rights reserveden_NZ
dc.rights.holderSociety for Industrial and Applied Mathematics, Activity Group on Data Mining and Analyticsen_NZ
dc.subjectoMTL (Online Multitask Learning with task selection)en_NZ
dc.subjecttask orderingen_NZ
dc.subjecteducational technologyen_NZ
dc.subject.marsden130306 Educational Technology and Computingen_NZ
dc.subject.marsden080109 Pattern Recognition and Data Miningen_NZ
dc.titleSmart task orderings for active online multitask learningen_NZ
dc.typeConference Contribution - Paper in Published Proceedingsen_NZ
unitec.conference.edate2014-04-26
unitec.conference.locationPhiladelphia, Pennsylvania, USA.en_NZ
unitec.conference.orgSociety for Industrial and Applied Mathematics, Activity Group on Data Mining and Analyticsen_NZ
unitec.conference.sdate2014-04-24
unitec.conference.title2014 SIAM International Conference on Data Miningen_NZ
unitec.identifier.roms56279en_NZ
unitec.identifier.roms56245
unitec.institutionUnitec Institute of Technologyen_NZ
unitec.institutionUniversity of Aucklanden_NZ
unitec.institutionNational Institute of Information and Communications Technology, Tokyo, Japanen_NZ
unitec.institution.studyareaComputing
unitec.peerreviewedyesen_NZ
unitec.publication.titleProceedings of SIAM International Conference on Data Miningen_NZ
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Smart Task Orderings for Active Online Multitask Learning.pdf
Size:
396.71 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description:
This item appears in: