A Robust Convex Formulation for Ensemble Clustering

Junning Gao; Makoto Yamada; Samuel Kaski; Hiroshi Mamitsuka; Shanfeng Zhu

A Robust Convex Formulation for Ensemble Clustering

Junning Gao, Makoto Yamada, Samuel Kaski, Hiroshi Mamitsuka, Shanfeng Zhu

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

3 Sitaatiot (Scopus)

95 Lataukset (Pure)

Abstrakti

We formulate ensemble clustering as a regularization problem over nuclear norm and cluster-wise group norm, and present an efficient optimization
algorithm, which we call Robust Convex Ensemble Clustering (RCEC). A key feature of RCEC allows to remove anomalous cluster assignments obtained
from component clustering methods by using the group-norm regularization. Moreover, the proposed method is convex and can find the globally optimal solution. We first showed that using synthetic data experiments, RCEC could learn stable cluster assignments from the input matrix including anomalous clusters. We then showed that RCEC outperformed state-of-the-art ensemble clustering methods by using real-world data sets.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16)
Toimittajat	Subbarao Kambhampati
Julkaisupaikka	2275 East Bayshore Road, Suite 160, Palo Alto CA 94303 USA
Kustantaja	AAAI PRESS
Sivut	1476-1482
Sivumäärä	6
ISBN (painettu)	978-1-57735-770-4
Tila	Julkaistu - heinäk. 2016
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	International Joint Conference on Artificial Intelligence - New York Hilton Midtown, New York, Yhdysvallat Kesto: 9 heinäk. 2016 → 15 heinäk. 2016 Konferenssinumero: 25 http://ijcai-16.org/index.php/welcome/view/home

Conference

Conference	International Joint Conference on Artificial Intelligence
Lyhennettä	IJCAI
Maa/Alue	Yhdysvallat
Kaupunki	New York
Ajanjakso	09/07/2016 → 15/07/2016
www-osoite	http://ijcai-16.org/index.php/welcome/view/home

Pääsy asiakirjaan

212Final published version, 824 KB

http://www.ijcai.org/Proceedings/16/Papers/212.pdf

SFX-saatavuus

Koko teksti

2 Päättynyt

Interaktiivinen koneoppiminen useista biodatalähteistä
Kaski, S. & Filstroff, L.
01/01/2016 → 31/08/2021
Projekti: Academy of Finland: Other research funding
Interaktiivinen koneoppiminen useista biodatalähteistä
Sundin, I., Hegde, P., Eranti, P., Kaski, S., Reinvall, J., Jälkö, J., Aushev, A., Celikok, M. M., Kangas, J., Honkamaa, J., Afrabandpey, H., Daee, P., Blomstedt, P., Chen, Y., Qin, X., Shen, Z., Peltola, T., Pesonen, H. & Siren, J.
01/01/2016 → 31/12/2018
Projekti: Academy of Finland: Other research funding

Siteeraa tätä

Gao, Junning ; Yamada, Makoto ; Kaski, Samuel ; Mamitsuka, Hiroshi ; Zhu, Shanfeng. / A Robust Convex Formulation for Ensemble Clustering. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16). Toimittaja / Subbarao Kambhampati. 2275 East Bayshore Road, Suite 160, Palo Alto CA 94303 USA : AAAI PRESS, 2016. Sivut 1476-1482

@inproceedings{90901dfe0a204f238bdf1a89e1b054b2,

title = "A Robust Convex Formulation for Ensemble Clustering",

abstract = "We formulate ensemble clustering as a regularization problem over nuclear norm and cluster-wise group norm, and present an efficient optimizationalgorithm, which we call Robust Convex Ensemble Clustering (RCEC). A key feature of RCEC allows to remove anomalous cluster assignments obtainedfrom component clustering methods by using the group-norm regularization. Moreover, the proposed method is convex and can find the globally optimal solution. We first showed that using synthetic data experiments, RCEC could learn stable cluster assignments from the input matrix including anomalous clusters. We then showed that RCEC outperformed state-of-the-art ensemble clustering methods by using real-world data sets.",

keywords = "ensemble clustering, convex optimization",

author = "Junning Gao and Makoto Yamada and Samuel Kaski and Hiroshi Mamitsuka and Shanfeng Zhu",

year = "2016",

month = jul,

language = "English",

isbn = "978-1-57735-770-4",

pages = "1476--1482",

editor = "Subbarao Kambhampati",

booktitle = "Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16)",

publisher = "AAAI PRESS",

note = "International Joint Conference on Artificial Intelligence, IJCAI ; Conference date: 09-07-2016 Through 15-07-2016",

url = "http://ijcai-16.org/index.php/welcome/view/home",

}

Gao, J, Yamada, M, Kaski, S , Mamitsuka, H & Zhu, S 2016, A Robust Convex Formulation for Ensemble Clustering. julkaisussa S Kambhampati (Toimittaja), Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16). AAAI PRESS, 2275 East Bayshore Road, Suite 160, Palo Alto CA 94303 USA, Sivut 1476-1482, International Joint Conference on Artificial Intelligence, New York, New York, Yhdysvallat, 09/07/2016. <http://www.ijcai.org/Proceedings/16/Papers/212.pdf>

A Robust Convex Formulation for Ensemble Clustering. / Gao, Junning; Yamada, Makoto; Kaski, Samuel ; Mamitsuka, Hiroshi; Zhu, Shanfeng.

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16). toim. / Subbarao Kambhampati. 2275 East Bayshore Road, Suite 160, Palo Alto CA 94303 USA : AAAI PRESS, 2016. s. 1476-1482.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

TY - GEN

T1 - A Robust Convex Formulation for Ensemble Clustering

AU - Gao, Junning

AU - Yamada, Makoto

AU - Kaski, Samuel

AU - Mamitsuka, Hiroshi

AU - Zhu, Shanfeng

N1 - Conference code: 25

PY - 2016/7

Y1 - 2016/7

N2 - We formulate ensemble clustering as a regularization problem over nuclear norm and cluster-wise group norm, and present an efficient optimizationalgorithm, which we call Robust Convex Ensemble Clustering (RCEC). A key feature of RCEC allows to remove anomalous cluster assignments obtainedfrom component clustering methods by using the group-norm regularization. Moreover, the proposed method is convex and can find the globally optimal solution. We first showed that using synthetic data experiments, RCEC could learn stable cluster assignments from the input matrix including anomalous clusters. We then showed that RCEC outperformed state-of-the-art ensemble clustering methods by using real-world data sets.

AB - We formulate ensemble clustering as a regularization problem over nuclear norm and cluster-wise group norm, and present an efficient optimizationalgorithm, which we call Robust Convex Ensemble Clustering (RCEC). A key feature of RCEC allows to remove anomalous cluster assignments obtainedfrom component clustering methods by using the group-norm regularization. Moreover, the proposed method is convex and can find the globally optimal solution. We first showed that using synthetic data experiments, RCEC could learn stable cluster assignments from the input matrix including anomalous clusters. We then showed that RCEC outperformed state-of-the-art ensemble clustering methods by using real-world data sets.

KW - ensemble clustering

KW - convex optimization

M3 - Conference contribution

SN - 978-1-57735-770-4

SP - 1476

EP - 1482

BT - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16)

A2 - Kambhampati, Subbarao

PB - AAAI PRESS

CY - 2275 East Bayshore Road, Suite 160, Palo Alto CA 94303 USA

T2 - International Joint Conference on Artificial Intelligence

Y2 - 9 July 2016 through 15 July 2016

ER -

A Robust Convex Formulation for Ensemble Clustering

Abstrakti

Conference

Pääsy asiakirjaan

SFX-saatavuus

Sormenjälki

Projektit

Interaktiivinen koneoppiminen useista biodatalähteistä

Interaktiivinen koneoppiminen useista biodatalähteistä

Siteeraa tätä