Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/68702
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Spectral Graph Partitioning Based on a Random Walk Diffusion Similarity Measure
Author: Li, X.
Hu, W.
Zhang, Z.
Liu, Y.
Citation: Computer Vision -- ACCV 2009: 9th Asian Conference on Computer Vision, Xi'an, China, September 23-27, 2009, Revised Selected Papers, Part II / H. Zha, R. Taniguchi and S. Maybank (eds.), pp.667-675
Publisher: Springer
Publisher Place: Berlin
Issue Date: 2010
ISBN: 9783642123030
ISSN: 0302-9743
1611-3349
Conference Name: Asian Conference on Computer Vision (9th : 2009 : Xi'an, China)
Statement of
Responsibility: 
Xi Li, Weiming Hu, Zhongfei Zhang, and Yang Liu
Abstract: Spectral graph partitioning is a powerful tool for unsupervised data learning. Most existing algorithms for spectral graph partitioning directly utilize the pairwise similarity matrix of the data to perform graph partitioning. Consequently, they are incapable of fully capturing the intrinsic structural information of graphs. To address this problem, we propose a novel random walk diffusion similarity measure (RWDSM) for capturing the intrinsic structural information of graphs. The RWDSM is composed of three key components—emission, absorbing, and transmission. It is proven that graph partitioning on the RWDSM matrix performs better than on the pairwise similarity matrix of the data. Moreover, a spectral graph partitioning objective function (referred to as DGPC) is used for capturing the discriminant information of graphs. The DGPC is designed to effectively characterize the intra-class compactness and the inter-class separability. Based on the RWDSM and DGPC, we further develop a novel spectral graph partitioning algorithm (referred to as DGPCA). Theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the developed DGPCA.
Description: Also published as a journal article: Lecture Notes in Computer Science, 2010; 5995: pp.667-675
Rights: © Springer-Verlag Berlin Heidelberg 2010
RMID: 0020112591
DOI: 10.1007/978-3-642-12304-7
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.