Outer-Points shaver: Robust graph-based clustering via node cutting

Younghoon Kim, Hyungrok Do, Seoung Bum Kim

Research output: Contribution to journalArticle

Abstract

Graph-based clustering is an efficient method for identifying clusters in local and nonlinear data patterns. Among the existing methods, spectral clustering is one of the most prominent algorithms. However, this method is vulnerable to noise and outliers. This study proposes a robust graph-based clustering method that removes the data nodes of relatively low density. The proposed method calculates the pseudo-density from a similarity matrix, and reconstructs it using a sparse regularization model. In this process, noise and the outer points are determined and removed. Unlike previous edge cutting-based methods, the proposed method is robust to noise while detecting clusters because it cuts out irrelevant nodes. We use a simulation and real-world data to demonstrate the usefulness of the proposed method by comparing it to existing methods in terms of clustering accuracy and robustness to noisy data. The comparison results confirm that the proposed method outperforms the alternatives.

Original languageEnglish
Article number107001
JournalPattern Recognition
Volume97
DOIs
Publication statusPublished - 2020 Jan 1

Keywords

  • Graph-based clustering
  • Node cutting
  • Pseudo-density reconstruction
  • Spectral clustering
  • Unsupervised learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Outer-Points shaver : Robust graph-based clustering via node cutting. / Kim, Younghoon; Do, Hyungrok; Kim, Seoung Bum.

In: Pattern Recognition, Vol. 97, 107001, 01.01.2020.

Research output: Contribution to journalArticle

@article{c3482ea8e42441c184092aa0c7557064,
title = "Outer-Points shaver: Robust graph-based clustering via node cutting",
abstract = "Graph-based clustering is an efficient method for identifying clusters in local and nonlinear data patterns. Among the existing methods, spectral clustering is one of the most prominent algorithms. However, this method is vulnerable to noise and outliers. This study proposes a robust graph-based clustering method that removes the data nodes of relatively low density. The proposed method calculates the pseudo-density from a similarity matrix, and reconstructs it using a sparse regularization model. In this process, noise and the outer points are determined and removed. Unlike previous edge cutting-based methods, the proposed method is robust to noise while detecting clusters because it cuts out irrelevant nodes. We use a simulation and real-world data to demonstrate the usefulness of the proposed method by comparing it to existing methods in terms of clustering accuracy and robustness to noisy data. The comparison results confirm that the proposed method outperforms the alternatives.",
keywords = "Graph-based clustering, Node cutting, Pseudo-density reconstruction, Spectral clustering, Unsupervised learning",
author = "Younghoon Kim and Hyungrok Do and Kim, {Seoung Bum}",
year = "2020",
month = "1",
day = "1",
doi = "10.1016/j.patcog.2019.107001",
language = "English",
volume = "97",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Outer-Points shaver

T2 - Robust graph-based clustering via node cutting

AU - Kim, Younghoon

AU - Do, Hyungrok

AU - Kim, Seoung Bum

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Graph-based clustering is an efficient method for identifying clusters in local and nonlinear data patterns. Among the existing methods, spectral clustering is one of the most prominent algorithms. However, this method is vulnerable to noise and outliers. This study proposes a robust graph-based clustering method that removes the data nodes of relatively low density. The proposed method calculates the pseudo-density from a similarity matrix, and reconstructs it using a sparse regularization model. In this process, noise and the outer points are determined and removed. Unlike previous edge cutting-based methods, the proposed method is robust to noise while detecting clusters because it cuts out irrelevant nodes. We use a simulation and real-world data to demonstrate the usefulness of the proposed method by comparing it to existing methods in terms of clustering accuracy and robustness to noisy data. The comparison results confirm that the proposed method outperforms the alternatives.

AB - Graph-based clustering is an efficient method for identifying clusters in local and nonlinear data patterns. Among the existing methods, spectral clustering is one of the most prominent algorithms. However, this method is vulnerable to noise and outliers. This study proposes a robust graph-based clustering method that removes the data nodes of relatively low density. The proposed method calculates the pseudo-density from a similarity matrix, and reconstructs it using a sparse regularization model. In this process, noise and the outer points are determined and removed. Unlike previous edge cutting-based methods, the proposed method is robust to noise while detecting clusters because it cuts out irrelevant nodes. We use a simulation and real-world data to demonstrate the usefulness of the proposed method by comparing it to existing methods in terms of clustering accuracy and robustness to noisy data. The comparison results confirm that the proposed method outperforms the alternatives.

KW - Graph-based clustering

KW - Node cutting

KW - Pseudo-density reconstruction

KW - Spectral clustering

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=85070685351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070685351&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2019.107001

DO - 10.1016/j.patcog.2019.107001

M3 - Article

AN - SCOPUS:85070685351

VL - 97

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

M1 - 107001

ER -