Robust Distributed Clustering Algorithm Over Multitask Networks

We propose a new adaptive clustering algorithm that is robust to various multitask environments. Positional relationships among optimal vectors and a reference signal are determined by using the mean-square deviation relation derived from a one-step least-mean-square update. Clustering is performed...

Full description

Bibliographic Details
Main Authors:	Jun-Taek Kong, Do-Chang Ahn, Seong-Eun Kim, Woo-Jin Song
Format:	Article
Language:	English
Published:	IEEE 2018-01-01
Series:	IEEE Access
Subjects:	Decentralized clustering multitask learning adaptive networks distributed estimation diffusion adaptation
Online Access:	https://ieeexplore.ieee.org/document/8429927/

id	doaj-d9bce5b379d842539b9996be7e375744
record_format	Article
spelling	doaj-d9bce5b379d842539b9996be7e3757442021-03-29T21:13:34ZengIEEEIEEE Access2169-35362018-01-016454394544710.1109/ACCESS.2018.28642058429927Robust Distributed Clustering Algorithm Over Multitask NetworksJun-Taek Kong0Do-Chang Ahn1Seong-Eun Kim2https://orcid.org/0000-0002-4518-4208Woo-Jin Song3Department of Electrical Engineering, Pohang University of Science and Technology, Pohang, South KoreaDepartment of Electrical Engineering, Pohang University of Science and Technology, Pohang, South KoreaDepartment of Electronics and Control Engineering, Hanbat National University, Daejeon, South KoreaDepartment of Electrical Engineering, Pohang University of Science and Technology, Pohang, South KoreaWe propose a new adaptive clustering algorithm that is robust to various multitask environments. Positional relationships among optimal vectors and a reference signal are determined by using the mean-square deviation relation derived from a one-step least-mean-square update. Clustering is performed by combining determinations on the positional relationships at several iterations. From this geometrical basis, unlike the conventional clustering algorithms using simple thresholding method, the proposed algorithm can perform clustering accurately in various multitask environments. Simulation results show that the proposed algorithm has more accurate estimation accuracy than the conventional algorithms and is insensitive to parameter selection.https://ieeexplore.ieee.org/document/8429927/Decentralized clusteringmultitask learningadaptive networksdistributed estimationdiffusion adaptation
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Jun-Taek Kong Do-Chang Ahn Seong-Eun Kim Woo-Jin Song
spellingShingle	Jun-Taek Kong Do-Chang Ahn Seong-Eun Kim Woo-Jin Song Robust Distributed Clustering Algorithm Over Multitask Networks IEEE Access Decentralized clustering multitask learning adaptive networks distributed estimation diffusion adaptation
author_facet	Jun-Taek Kong Do-Chang Ahn Seong-Eun Kim Woo-Jin Song
author_sort	Jun-Taek Kong
title	Robust Distributed Clustering Algorithm Over Multitask Networks
title_short	Robust Distributed Clustering Algorithm Over Multitask Networks
title_full	Robust Distributed Clustering Algorithm Over Multitask Networks
title_fullStr	Robust Distributed Clustering Algorithm Over Multitask Networks
title_full_unstemmed	Robust Distributed Clustering Algorithm Over Multitask Networks
title_sort	robust distributed clustering algorithm over multitask networks
publisher	IEEE
series	IEEE Access
issn	2169-3536
publishDate	2018-01-01
description	We propose a new adaptive clustering algorithm that is robust to various multitask environments. Positional relationships among optimal vectors and a reference signal are determined by using the mean-square deviation relation derived from a one-step least-mean-square update. Clustering is performed by combining determinations on the positional relationships at several iterations. From this geometrical basis, unlike the conventional clustering algorithms using simple thresholding method, the proposed algorithm can perform clustering accurately in various multitask environments. Simulation results show that the proposed algorithm has more accurate estimation accuracy than the conventional algorithms and is insensitive to parameter selection.
topic	Decentralized clustering multitask learning adaptive networks distributed estimation diffusion adaptation
url	https://ieeexplore.ieee.org/document/8429927/
work_keys_str_mv	AT juntaekkong robustdistributedclusteringalgorithmovermultitasknetworks AT dochangahn robustdistributedclusteringalgorithmovermultitasknetworks AT seongeunkim robustdistributedclusteringalgorithmovermultitasknetworks AT woojinsong robustdistributedclusteringalgorithmovermultitasknetworks
_version_	1724193353009987584

Robust Distributed Clustering Algorithm Over Multitask Networks

Similar Items