Cheetah: Fast graph kernel tracking on dynamic graphs

Liangyue Li, Hanghang Tong, Yanghua Xiao, Wei Fan

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

  • 4 Citations

Abstract

Graph kernels provide an expressive approach to measuring the similarity of two graphs, and are key building blocks behind many real-world applications, such as bioinformatics, brain science and social networks. However, current methods for computing graph kernels assume the input graphs are static, which is often not the case in reality. It is highly desirable to track the graph kernels on dynamic graphs evolving over time in a timely manner. In this paper, we propose a family of Cheetah algorithms to deal with the challenge. Cheetah leverages the low rank structure of graph updates and incrementally updates the eigen-decomposition or SVD of the adjacency matrices of graphs. Experimental evaluations on real world graphs validate our algorithms (1) are significantly faster than alternatives with high accuracy and (b) scale sub-linearly.

LanguageEnglish (US)
Title of host publicationSIAM International Conference on Data Mining 2015, SDM 2015
PublisherSociety for Industrial and Applied Mathematics Publications
Pages280-288
Number of pages9
ISBN (Print)9781510811522
StatePublished - 2015
EventSIAM International Conference on Data Mining 2015, SDM 2015 - Vancouver, Canada
Duration: Apr 30 2015May 2 2015

Other

OtherSIAM International Conference on Data Mining 2015, SDM 2015
CountryCanada
CityVancouver
Period4/30/155/2/15

Fingerprint

Singular value decomposition
Bioinformatics
Brain
Decomposition

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Li, L., Tong, H., Xiao, Y., & Fan, W. (2015). Cheetah: Fast graph kernel tracking on dynamic graphs. In SIAM International Conference on Data Mining 2015, SDM 2015 (pp. 280-288). Society for Industrial and Applied Mathematics Publications.

Cheetah : Fast graph kernel tracking on dynamic graphs. / Li, Liangyue; Tong, Hanghang; Xiao, Yanghua; Fan, Wei.

SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, 2015. p. 280-288.

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

Li, L, Tong, H, Xiao, Y & Fan, W 2015, Cheetah: Fast graph kernel tracking on dynamic graphs. in SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, pp. 280-288, SIAM International Conference on Data Mining 2015, SDM 2015, Vancouver, Canada, 4/30/15.
Li L, Tong H, Xiao Y, Fan W. Cheetah: Fast graph kernel tracking on dynamic graphs. In SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications. 2015. p. 280-288
Li, Liangyue ; Tong, Hanghang ; Xiao, Yanghua ; Fan, Wei. / Cheetah : Fast graph kernel tracking on dynamic graphs. SIAM International Conference on Data Mining 2015, SDM 2015. Society for Industrial and Applied Mathematics Publications, 2015. pp. 280-288
@inproceedings{47c737db97774541b4ec6c5d7937774c,
title = "Cheetah: Fast graph kernel tracking on dynamic graphs",
abstract = "Graph kernels provide an expressive approach to measuring the similarity of two graphs, and are key building blocks behind many real-world applications, such as bioinformatics, brain science and social networks. However, current methods for computing graph kernels assume the input graphs are static, which is often not the case in reality. It is highly desirable to track the graph kernels on dynamic graphs evolving over time in a timely manner. In this paper, we propose a family of Cheetah algorithms to deal with the challenge. Cheetah leverages the low rank structure of graph updates and incrementally updates the eigen-decomposition or SVD of the adjacency matrices of graphs. Experimental evaluations on real world graphs validate our algorithms (1) are significantly faster than alternatives with high accuracy and (b) scale sub-linearly.",
author = "Liangyue Li and Hanghang Tong and Yanghua Xiao and Wei Fan",
year = "2015",
language = "English (US)",
isbn = "9781510811522",
pages = "280--288",
booktitle = "SIAM International Conference on Data Mining 2015, SDM 2015",
publisher = "Society for Industrial and Applied Mathematics Publications",

}

TY - GEN

T1 - Cheetah

T2 - Fast graph kernel tracking on dynamic graphs

AU - Li, Liangyue

AU - Tong, Hanghang

AU - Xiao, Yanghua

AU - Fan, Wei

PY - 2015

Y1 - 2015

N2 - Graph kernels provide an expressive approach to measuring the similarity of two graphs, and are key building blocks behind many real-world applications, such as bioinformatics, brain science and social networks. However, current methods for computing graph kernels assume the input graphs are static, which is often not the case in reality. It is highly desirable to track the graph kernels on dynamic graphs evolving over time in a timely manner. In this paper, we propose a family of Cheetah algorithms to deal with the challenge. Cheetah leverages the low rank structure of graph updates and incrementally updates the eigen-decomposition or SVD of the adjacency matrices of graphs. Experimental evaluations on real world graphs validate our algorithms (1) are significantly faster than alternatives with high accuracy and (b) scale sub-linearly.

AB - Graph kernels provide an expressive approach to measuring the similarity of two graphs, and are key building blocks behind many real-world applications, such as bioinformatics, brain science and social networks. However, current methods for computing graph kernels assume the input graphs are static, which is often not the case in reality. It is highly desirable to track the graph kernels on dynamic graphs evolving over time in a timely manner. In this paper, we propose a family of Cheetah algorithms to deal with the challenge. Cheetah leverages the low rank structure of graph updates and incrementally updates the eigen-decomposition or SVD of the adjacency matrices of graphs. Experimental evaluations on real world graphs validate our algorithms (1) are significantly faster than alternatives with high accuracy and (b) scale sub-linearly.

UR - http://www.scopus.com/inward/record.url?scp=84961926584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961926584&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781510811522

SP - 280

EP - 288

BT - SIAM International Conference on Data Mining 2015, SDM 2015

PB - Society for Industrial and Applied Mathematics Publications

ER -