Effective graph classification based on topological and label attributes

Geng Li, Murat Semerci, Bülent Yener, Mohammed J. Zaki

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

Graph classification is an important data mining task, and various graph kernel methods have been proposed recently for this task. These methods have proven to be effective, but they tend to have high computational overhead. In this paper, we propose an alternative approach to graph classification that is based on feature vectors constructed from different global topological attributes, as well as global label features. The main idea is that the graphs from the same class should have similar topological and label attributes. Our method is simple and easy to implement, and via a detailed comparison on real benchmark datasets, we show that our topological and label feature-based approach delivers competitive classification accuracy, with significantly better results on those datasets that have large unlabeled graph instances. Our method is also substantially faster than most other graph kernels.

Original languageEnglish
Pages (from-to)265-283
Number of pages19
JournalStatistical Analysis and Data Mining
Volume5
Issue number4
DOIs
Publication statusPublished - 1 Aug 2012
Externally publishedYes

Fingerprint

Labels
Attribute
Graph in graph theory
Data mining
Kernel Methods
Feature Vector
Data Mining
Tend
Benchmark
kernel
Alternatives

Keywords

  • Graph classification
  • Graph kernels
  • Graph mining
  • Topological attributes

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Analysis

Cite this

Effective graph classification based on topological and label attributes. / Li, Geng; Semerci, Murat; Yener, Bülent; Zaki, Mohammed J.

In: Statistical Analysis and Data Mining, Vol. 5, No. 4, 01.08.2012, p. 265-283.

Research output: Contribution to journalArticle

Li, Geng ; Semerci, Murat ; Yener, Bülent ; Zaki, Mohammed J. / Effective graph classification based on topological and label attributes. In: Statistical Analysis and Data Mining. 2012 ; Vol. 5, No. 4. pp. 265-283.
@article{973df22b0d6644bcbc0c3ebef627cd6c,
title = "Effective graph classification based on topological and label attributes",
abstract = "Graph classification is an important data mining task, and various graph kernel methods have been proposed recently for this task. These methods have proven to be effective, but they tend to have high computational overhead. In this paper, we propose an alternative approach to graph classification that is based on feature vectors constructed from different global topological attributes, as well as global label features. The main idea is that the graphs from the same class should have similar topological and label attributes. Our method is simple and easy to implement, and via a detailed comparison on real benchmark datasets, we show that our topological and label feature-based approach delivers competitive classification accuracy, with significantly better results on those datasets that have large unlabeled graph instances. Our method is also substantially faster than most other graph kernels.",
keywords = "Graph classification, Graph kernels, Graph mining, Topological attributes",
author = "Geng Li and Murat Semerci and B{\"u}lent Yener and Zaki, {Mohammed J.}",
year = "2012",
month = "8",
day = "1",
doi = "10.1002/sam.11153",
language = "English",
volume = "5",
pages = "265--283",
journal = "Statistical Analysis and Data Mining",
issn = "1932-1872",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Effective graph classification based on topological and label attributes

AU - Li, Geng

AU - Semerci, Murat

AU - Yener, Bülent

AU - Zaki, Mohammed J.

PY - 2012/8/1

Y1 - 2012/8/1

N2 - Graph classification is an important data mining task, and various graph kernel methods have been proposed recently for this task. These methods have proven to be effective, but they tend to have high computational overhead. In this paper, we propose an alternative approach to graph classification that is based on feature vectors constructed from different global topological attributes, as well as global label features. The main idea is that the graphs from the same class should have similar topological and label attributes. Our method is simple and easy to implement, and via a detailed comparison on real benchmark datasets, we show that our topological and label feature-based approach delivers competitive classification accuracy, with significantly better results on those datasets that have large unlabeled graph instances. Our method is also substantially faster than most other graph kernels.

AB - Graph classification is an important data mining task, and various graph kernel methods have been proposed recently for this task. These methods have proven to be effective, but they tend to have high computational overhead. In this paper, we propose an alternative approach to graph classification that is based on feature vectors constructed from different global topological attributes, as well as global label features. The main idea is that the graphs from the same class should have similar topological and label attributes. Our method is simple and easy to implement, and via a detailed comparison on real benchmark datasets, we show that our topological and label feature-based approach delivers competitive classification accuracy, with significantly better results on those datasets that have large unlabeled graph instances. Our method is also substantially faster than most other graph kernels.

KW - Graph classification

KW - Graph kernels

KW - Graph mining

KW - Topological attributes

UR - http://www.scopus.com/inward/record.url?scp=84864032087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864032087&partnerID=8YFLogxK

U2 - 10.1002/sam.11153

DO - 10.1002/sam.11153

M3 - Article

VL - 5

SP - 265

EP - 283

JO - Statistical Analysis and Data Mining

JF - Statistical Analysis and Data Mining

SN - 1932-1872

IS - 4

ER -