LABIN: Balanced Min Cut for Large-Scale Data

Xiaojun Chen; Renjie Chen; Qingyao Wu; Yixiang Fang; Feiping Nie; Joshua Zhexue Huang

doi:10.1109/TNNLS.2019.2909425

LABIN: Balanced Min Cut for Large-Scale Data

Xiaojun Chen, Renjie Chen, Qingyao Wu, Yixiang Fang, Feiping Nie, Joshua Zhexue Huang

School of Artificial Intelligence, OPtics and Electronics

Research output: Contribution to journal › Article › peer-review

30 Scopus citations

Abstract

Although many spectral clustering algorithms have been proposed during the past decades, they are not scalable to large-scale data due to their high computational complexities. In this paper, we propose a novel spectral clustering method for large-scale data, namely, large-scale balanced min cut (LABIN). A new model is proposed to extend the self-balanced min-cut (SBMC) model with the anchor-based strategy and a fast spectral rotation with linear time complexity is proposed to solve the new model. Extensive experimental results show the superior performance of our proposed method in comparison with the state-of-the-art methods including SBMC.

Original language	English
Article number	8712566
Pages (from-to)	725-736
Number of pages	12
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	31
Issue number	3
DOIs	https://doi.org/10.1109/TNNLS.2019.2909425
State	Published - Mar 2020

Keywords

Clustering
graph cut
large-scale data
spectral clustering

Access to Document

10.1109/TNNLS.2019.2909425

Cite this

@article{980f796d03eb476f81b5696cbb63dec8,

title = "LABIN: Balanced Min Cut for Large-Scale Data",

abstract = "Although many spectral clustering algorithms have been proposed during the past decades, they are not scalable to large-scale data due to their high computational complexities. In this paper, we propose a novel spectral clustering method for large-scale data, namely, large-scale balanced min cut (LABIN). A new model is proposed to extend the self-balanced min-cut (SBMC) model with the anchor-based strategy and a fast spectral rotation with linear time complexity is proposed to solve the new model. Extensive experimental results show the superior performance of our proposed method in comparison with the state-of-the-art methods including SBMC.",

keywords = "Clustering, graph cut, large-scale data, spectral clustering",

author = "Xiaojun Chen and Renjie Chen and Qingyao Wu and Yixiang Fang and Feiping Nie and Huang, {Joshua Zhexue}",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2020",

month = mar,

doi = "10.1109/TNNLS.2019.2909425",

language = "英语",

volume = "31",

pages = "725--736",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "3",

}

TY - JOUR

T1 - LABIN

T2 - Balanced Min Cut for Large-Scale Data

AU - Chen, Xiaojun

AU - Chen, Renjie

AU - Wu, Qingyao

AU - Fang, Yixiang

AU - Nie, Feiping

AU - Huang, Joshua Zhexue

PY - 2020/3

Y1 - 2020/3

N2 - Although many spectral clustering algorithms have been proposed during the past decades, they are not scalable to large-scale data due to their high computational complexities. In this paper, we propose a novel spectral clustering method for large-scale data, namely, large-scale balanced min cut (LABIN). A new model is proposed to extend the self-balanced min-cut (SBMC) model with the anchor-based strategy and a fast spectral rotation with linear time complexity is proposed to solve the new model. Extensive experimental results show the superior performance of our proposed method in comparison with the state-of-the-art methods including SBMC.

AB - Although many spectral clustering algorithms have been proposed during the past decades, they are not scalable to large-scale data due to their high computational complexities. In this paper, we propose a novel spectral clustering method for large-scale data, namely, large-scale balanced min cut (LABIN). A new model is proposed to extend the self-balanced min-cut (SBMC) model with the anchor-based strategy and a fast spectral rotation with linear time complexity is proposed to solve the new model. Extensive experimental results show the superior performance of our proposed method in comparison with the state-of-the-art methods including SBMC.

KW - Clustering

KW - graph cut

KW - large-scale data

KW - spectral clustering

UR - http://www.scopus.com/inward/record.url?scp=85079537902&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2019.2909425

DO - 10.1109/TNNLS.2019.2909425

M3 - 文章

C2 - 31094694

AN - SCOPUS:85079537902

SN - 2162-237X

VL - 31

SP - 725

EP - 736

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 3

M1 - 8712566

ER -

LABIN: Balanced Min Cut for Large-Scale Data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this