A scalable signal processing architecture for massive graph analysis

Benjamin A. Miller, Nicholas Arcolano, Michelle S. Beard, Jeremy Kepner, Matthew C. Schmidt, Nadya Bliss, Patrick J. Wolfe

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

16 Citations (Scopus)

Abstract

In many applications, it is convenient to represent data as a graph, and often these datasets will be quite large. This paper presents an architecture for analyzing massive graphs, with a focus on signal processing applications such as modeling, filtering, and signal detection. We describe the architecture, which covers the entire processing chain, from data storage to graph construction to graph analysis and subgraph detection. The data are stored in a new format that allows easy extraction of graphs representing any relationship existing in the data. The principal analysis algorithm is the partial eigendecomposition of the modularity matrix, whose running time is discussed. A large document dataset is analyzed, and we present subgraphs that stand out in the principal eigenspace of the time-varying graphs, including behavior we regard as clutter as well as small, tightly-connected clusters that emerge over time.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages5329-5332
Number of pages4
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan
Duration: Mar 25 2012Mar 30 2012

Other

Other2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
CountryJapan
CityKyoto
Period3/25/123/30/12

Fingerprint

Signal processing
Signal detection
Data storage equipment
Processing

Keywords

  • emergent behavior
  • Graph theory
  • large data analysis
  • processing architectures
  • residuals analysis

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Miller, B. A., Arcolano, N., Beard, M. S., Kepner, J., Schmidt, M. C., Bliss, N., & Wolfe, P. J. (2012). A scalable signal processing architecture for massive graph analysis. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 5329-5332). [6289124] https://doi.org/10.1109/ICASSP.2012.6289124

A scalable signal processing architecture for massive graph analysis. / Miller, Benjamin A.; Arcolano, Nicholas; Beard, Michelle S.; Kepner, Jeremy; Schmidt, Matthew C.; Bliss, Nadya; Wolfe, Patrick J.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2012. p. 5329-5332 6289124.

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

Miller, BA, Arcolano, N, Beard, MS, Kepner, J, Schmidt, MC, Bliss, N & Wolfe, PJ 2012, A scalable signal processing architecture for massive graph analysis. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6289124, pp. 5329-5332, 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japan, 3/25/12. https://doi.org/10.1109/ICASSP.2012.6289124
Miller BA, Arcolano N, Beard MS, Kepner J, Schmidt MC, Bliss N et al. A scalable signal processing architecture for massive graph analysis. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2012. p. 5329-5332. 6289124 https://doi.org/10.1109/ICASSP.2012.6289124
Miller, Benjamin A. ; Arcolano, Nicholas ; Beard, Michelle S. ; Kepner, Jeremy ; Schmidt, Matthew C. ; Bliss, Nadya ; Wolfe, Patrick J. / A scalable signal processing architecture for massive graph analysis. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2012. pp. 5329-5332
@inproceedings{ea2fbc4ddb0d4cc297916d1f340d9d11,
title = "A scalable signal processing architecture for massive graph analysis",
abstract = "In many applications, it is convenient to represent data as a graph, and often these datasets will be quite large. This paper presents an architecture for analyzing massive graphs, with a focus on signal processing applications such as modeling, filtering, and signal detection. We describe the architecture, which covers the entire processing chain, from data storage to graph construction to graph analysis and subgraph detection. The data are stored in a new format that allows easy extraction of graphs representing any relationship existing in the data. The principal analysis algorithm is the partial eigendecomposition of the modularity matrix, whose running time is discussed. A large document dataset is analyzed, and we present subgraphs that stand out in the principal eigenspace of the time-varying graphs, including behavior we regard as clutter as well as small, tightly-connected clusters that emerge over time.",
keywords = "emergent behavior, Graph theory, large data analysis, processing architectures, residuals analysis",
author = "Miller, {Benjamin A.} and Nicholas Arcolano and Beard, {Michelle S.} and Jeremy Kepner and Schmidt, {Matthew C.} and Nadya Bliss and Wolfe, {Patrick J.}",
year = "2012",
doi = "10.1109/ICASSP.2012.6289124",
language = "English (US)",
isbn = "9781467300469",
pages = "5329--5332",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - A scalable signal processing architecture for massive graph analysis

AU - Miller, Benjamin A.

AU - Arcolano, Nicholas

AU - Beard, Michelle S.

AU - Kepner, Jeremy

AU - Schmidt, Matthew C.

AU - Bliss, Nadya

AU - Wolfe, Patrick J.

PY - 2012

Y1 - 2012

N2 - In many applications, it is convenient to represent data as a graph, and often these datasets will be quite large. This paper presents an architecture for analyzing massive graphs, with a focus on signal processing applications such as modeling, filtering, and signal detection. We describe the architecture, which covers the entire processing chain, from data storage to graph construction to graph analysis and subgraph detection. The data are stored in a new format that allows easy extraction of graphs representing any relationship existing in the data. The principal analysis algorithm is the partial eigendecomposition of the modularity matrix, whose running time is discussed. A large document dataset is analyzed, and we present subgraphs that stand out in the principal eigenspace of the time-varying graphs, including behavior we regard as clutter as well as small, tightly-connected clusters that emerge over time.

AB - In many applications, it is convenient to represent data as a graph, and often these datasets will be quite large. This paper presents an architecture for analyzing massive graphs, with a focus on signal processing applications such as modeling, filtering, and signal detection. We describe the architecture, which covers the entire processing chain, from data storage to graph construction to graph analysis and subgraph detection. The data are stored in a new format that allows easy extraction of graphs representing any relationship existing in the data. The principal analysis algorithm is the partial eigendecomposition of the modularity matrix, whose running time is discussed. A large document dataset is analyzed, and we present subgraphs that stand out in the principal eigenspace of the time-varying graphs, including behavior we regard as clutter as well as small, tightly-connected clusters that emerge over time.

KW - emergent behavior

KW - Graph theory

KW - large data analysis

KW - processing architectures

KW - residuals analysis

UR - http://www.scopus.com/inward/record.url?scp=84867619540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867619540&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2012.6289124

DO - 10.1109/ICASSP.2012.6289124

M3 - Conference contribution

SN - 9781467300469

SP - 5329

EP - 5332

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -