Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/82962
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhang, Chien
dc.contributor.authorZhao, Peilinen
dc.contributor.authorHao, Shujien
dc.contributor.authorSoh, Yeng Chaien
dc.contributor.authorLee, Bu Sungen
dc.contributor.authorMiao, Chunyanen
dc.contributor.authorHoi, Steven C. H.en
dc.date.accessioned2019-07-03T02:56:29Zen
dc.date.accessioned2019-12-06T15:09:04Z-
dc.date.available2019-07-03T02:56:29Zen
dc.date.available2019-12-06T15:09:04Z-
dc.date.issued2018en
dc.identifier.citationZhang, C., Zhao, P., Hao, S., Soh, Y. C., Lee, B. S., Miao, C., & Hoi, S. C. H. (2018). Distributed multi-task classification: a decentralized online learning approach. Machine Learning, 107(4), 727-747. doi:10.1007/s10994-017-5676-yen
dc.identifier.issn0885-6125en
dc.identifier.urihttps://hdl.handle.net/10356/82962-
dc.description.abstractAlthough dispersing one single task to distributed learning nodes has been intensively studied by the previous research, multi-task learning on distributed networks is still an area that has not been fully exploited, especially under decentralized settings. The challenge lies in the fact that different tasks may have different optimal learning weights while communication through the distributed network forces all tasks to converge to an unique classifier. In this paper, we present a novel algorithm to overcome this challenge and enable learning multiple tasks simultaneously on a decentralized distributed network. Specifically, the learning framework can be separated into two phases: (i) multi-task information is shared within each node on the first phase; (ii) communication between nodes then leads the whole network to converge to a common minimizer. Theoretical analysis indicates that our algorithm achieves a O(T−−√) regret bound when compared with the best classifier in hindsight, which is further validated by experiments on both synthetic and real-world datasets.en
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en
dc.language.isoenen
dc.relation.ispartofseriesMachine Learningen
dc.rights© 2017 The Author(s). All rights reserved.en
dc.subjectDecentralized Distributed Learningen
dc.subjectMulti-task Learningen
dc.subjectEngineering::Electrical and electronic engineeringen
dc.titleDistributed multi-task classification : a decentralized online learning approachen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.identifier.doi10.1007/s10994-017-5676-yen
item.fulltextNo Fulltext-
item.grantfulltextnone-
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 20

25
Updated on Jun 7, 2024

Web of ScienceTM
Citations 20

22
Updated on Oct 20, 2023

Page view(s) 20

662
Updated on Jun 14, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.