Large scale data clustering and graph partitioning via simulated mixing

Shahzad Bhatti, Carolyn Beck, Angelia Nedich

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a new spectral clustering algorithm relying on a simulated mixing process over a graph. In contrast to existing spectral clustering algorithms, our algorithm does not necessitate the computation of eigenvectors. Alternatively, our algorithm determines the equivalent of a linear combination of eigenvectors of the normalized similarity matrix, which are weighted by the corresponding eigenvalues obtained by the mixing process on the graph. We use the information gained from this linear combination of eigenvectors directly to partition the dataset into meaningful clusters. Simulations on real datasets show that our algorithm achieves better accuracy than standard spectral clustering methods as the number of clusters increase.

Original languageEnglish (US)
Title of host publication2016 IEEE 55th Conference on Decision and Control, CDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages147-152
Number of pages6
ISBN (Electronic)9781509018376
DOIs
StatePublished - Dec 27 2016
Event55th IEEE Conference on Decision and Control, CDC 2016 - Las Vegas, United States
Duration: Dec 12 2016Dec 14 2016

Other

Other55th IEEE Conference on Decision and Control, CDC 2016
CountryUnited States
CityLas Vegas
Period12/12/1612/14/16

Fingerprint

Spectral Clustering
Graph Partitioning
Data Clustering
Eigenvalues and eigenfunctions
Eigenvector
Mixing Processes
Clustering algorithms
Clustering Algorithm
Linear Combination
Number of Clusters
Graph in graph theory
Spectral Methods
Clustering Methods
Partition
Eigenvalue
Partitioning
Data clustering
Graph
Simulation
Clustering algorithm

ASJC Scopus subject areas

  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Control and Optimization

Cite this

Bhatti, S., Beck, C., & Nedich, A. (2016). Large scale data clustering and graph partitioning via simulated mixing. In 2016 IEEE 55th Conference on Decision and Control, CDC 2016 (pp. 147-152). [7798261] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC.2016.7798261

Large scale data clustering and graph partitioning via simulated mixing. / Bhatti, Shahzad; Beck, Carolyn; Nedich, Angelia.

2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 147-152 7798261.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bhatti, S, Beck, C & Nedich, A 2016, Large scale data clustering and graph partitioning via simulated mixing. in 2016 IEEE 55th Conference on Decision and Control, CDC 2016., 7798261, Institute of Electrical and Electronics Engineers Inc., pp. 147-152, 55th IEEE Conference on Decision and Control, CDC 2016, Las Vegas, United States, 12/12/16. https://doi.org/10.1109/CDC.2016.7798261
Bhatti S, Beck C, Nedich A. Large scale data clustering and graph partitioning via simulated mixing. In 2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 147-152. 7798261 https://doi.org/10.1109/CDC.2016.7798261
Bhatti, Shahzad ; Beck, Carolyn ; Nedich, Angelia. / Large scale data clustering and graph partitioning via simulated mixing. 2016 IEEE 55th Conference on Decision and Control, CDC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 147-152
@inproceedings{5bbb903d14874c7c8125d5cd120c804e,
title = "Large scale data clustering and graph partitioning via simulated mixing",
abstract = "In this paper, we propose a new spectral clustering algorithm relying on a simulated mixing process over a graph. In contrast to existing spectral clustering algorithms, our algorithm does not necessitate the computation of eigenvectors. Alternatively, our algorithm determines the equivalent of a linear combination of eigenvectors of the normalized similarity matrix, which are weighted by the corresponding eigenvalues obtained by the mixing process on the graph. We use the information gained from this linear combination of eigenvectors directly to partition the dataset into meaningful clusters. Simulations on real datasets show that our algorithm achieves better accuracy than standard spectral clustering methods as the number of clusters increase.",
author = "Shahzad Bhatti and Carolyn Beck and Angelia Nedich",
year = "2016",
month = "12",
day = "27",
doi = "10.1109/CDC.2016.7798261",
language = "English (US)",
pages = "147--152",
booktitle = "2016 IEEE 55th Conference on Decision and Control, CDC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Large scale data clustering and graph partitioning via simulated mixing

AU - Bhatti, Shahzad

AU - Beck, Carolyn

AU - Nedich, Angelia

PY - 2016/12/27

Y1 - 2016/12/27

N2 - In this paper, we propose a new spectral clustering algorithm relying on a simulated mixing process over a graph. In contrast to existing spectral clustering algorithms, our algorithm does not necessitate the computation of eigenvectors. Alternatively, our algorithm determines the equivalent of a linear combination of eigenvectors of the normalized similarity matrix, which are weighted by the corresponding eigenvalues obtained by the mixing process on the graph. We use the information gained from this linear combination of eigenvectors directly to partition the dataset into meaningful clusters. Simulations on real datasets show that our algorithm achieves better accuracy than standard spectral clustering methods as the number of clusters increase.

AB - In this paper, we propose a new spectral clustering algorithm relying on a simulated mixing process over a graph. In contrast to existing spectral clustering algorithms, our algorithm does not necessitate the computation of eigenvectors. Alternatively, our algorithm determines the equivalent of a linear combination of eigenvectors of the normalized similarity matrix, which are weighted by the corresponding eigenvalues obtained by the mixing process on the graph. We use the information gained from this linear combination of eigenvectors directly to partition the dataset into meaningful clusters. Simulations on real datasets show that our algorithm achieves better accuracy than standard spectral clustering methods as the number of clusters increase.

UR - http://www.scopus.com/inward/record.url?scp=85010715803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010715803&partnerID=8YFLogxK

U2 - 10.1109/CDC.2016.7798261

DO - 10.1109/CDC.2016.7798261

M3 - Conference contribution

AN - SCOPUS:85010715803

SP - 147

EP - 152

BT - 2016 IEEE 55th Conference on Decision and Control, CDC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -