Fully-Decentralized Multi-Kernel Online Learning over Networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chae, Jeongmin | - |
dc.contributor.author | Mitra, Urbashi | - |
dc.contributor.author | Hong, Songnam | - |
dc.date.accessioned | 2022-07-06T08:50:05Z | - |
dc.date.available | 2022-07-06T08:50:05Z | - |
dc.date.created | 2022-05-04 | - |
dc.date.issued | 2022-02 | - |
dc.identifier.issn | 2334-0983 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139468 | - |
dc.description.abstract | Fully decentralized online learning with multiple kernels (named FDOMKL) is studied, where each node in a network learns a sequence of global functions in an online fashion without the control of a central server. Every node finds the best global function only using information from its one-hop neighboring nodes via online alternating direction method of multipliers (ADMM) and the network-wise Hedge algorithm. The learning framework for an individual node is based on kernel learning and the proposed algorithm successfully harness multi-kernel method to find the best common function over the entire network. To the best of our knowledge, this is the first work that proposes a fully-decentralized online learning algorithm based on multiple kernels. The proposed FDOMKL preserves privacy by maintaining the local data at the edge nodes and exchanging model parameters only. We prove that FDOMKL achieves a sublinear regret bound compared with the best kernel function in hindsight under certain assumptions. In addition, numerical tests on real time-series datasets demonstrate the superiority of the proposed algorithm in terms of learning accuracy and network consistency compared to state-of-the-art single kernel methods. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Fully-Decentralized Multi-Kernel Online Learning over Networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Hong, Songnam | - |
dc.identifier.doi | 10.1109/GLOBECOM46510.2021.9685264 | - |
dc.identifier.scopusid | 2-s2.0-85127243286 | - |
dc.identifier.wosid | 000790747201052 | - |
dc.identifier.bibliographicCitation | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings, pp.1 - 6 | - |
dc.relation.isPartOf | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings | - |
dc.citation.title | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 6 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | E-learning | - |
dc.subject.keywordPlus | Learning algorithms | - |
dc.subject.keywordPlus | Numerical methods | - |
dc.subject.keywordPlus | Convex optimization | - |
dc.subject.keywordPlus | Decentralised | - |
dc.subject.keywordPlus | Decentralized learning | - |
dc.subject.keywordPlus | Global functions | - |
dc.subject.keywordPlus | Kernel-methods | - |
dc.subject.keywordPlus | Learn+ | - |
dc.subject.keywordPlus | Multi-kernel | - |
dc.subject.keywordPlus | Multi-kernel learning | - |
dc.subject.keywordPlus | Multiple kernels | - |
dc.subject.keywordPlus | Online convex optimizations | - |
dc.subject.keywordPlus | Online learning | - |
dc.subject.keywordAuthor | Decentralized learning | - |
dc.subject.keywordAuthor | multi-kernel learning | - |
dc.subject.keywordAuthor | online convex optimization | - |
dc.subject.keywordAuthor | online learning | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9685264 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.