Welcome to the InfoSci Platform
A Comparative Study of Graph Kernels and Clustering Algorithms

A Comparative Study of Graph Kernels and Clustering Algorithms

Riju Bhattacharya, Naresh Kumar Nagwani, Sarsij Tripathi
Copyright: © 2021 |Volume: 12 |Issue: 1 |Pages: 16
ISSN: 1947-8534|EISSN: 1947-8542|EISBN13: 9781799860488|DOI: 10.4018/IJMDEM.2021010103
Cite Article Cite Article

MLA

Bhattacharya, Riju, et al. "A Comparative Study of Graph Kernels and Clustering Algorithms." IJMDEM vol.12, no.1 2021: pp.33-48. http://doi.org/10.4018/IJMDEM.2021010103

APA

Bhattacharya, R., Nagwani, N. K., & Tripathi, S. (2021). A Comparative Study of Graph Kernels and Clustering Algorithms. International Journal of Multimedia Data Engineering and Management (IJMDEM), 12(1), 33-48. http://doi.org/10.4018/IJMDEM.2021010103

Chicago

Bhattacharya, Riju, Naresh Kumar Nagwani, and Sarsij Tripathi. "A Comparative Study of Graph Kernels and Clustering Algorithms," International Journal of Multimedia Data Engineering and Management (IJMDEM) 12, no.1: 33-48. http://doi.org/10.4018/IJMDEM.2021010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Graph kernels have evolved as a promising and popular method for graph clustering over the last decade. In this work, comparative study on the five standard graph kernel techniques for graph clustering has been performed. The graph kernels, namely vertex histogram kernel, shortest path kernel, graphlet kernel, k-step random walk kernel, and Weisfeiler-Lehman kernel have been compared for graph clustering. The clustering methods considered for the kernel comparison are hierarchical, k-means, model-based, fuzzy-based, and self-organizing map clustering techniques. The comparative study of kernel methods over the clustering techniques is performed on MUTAG benchmark dataset. Clustering performance is assessed with internal validation performance parameters such as connectivity, Dunn, and the silhouette index. Finally, the comparative analysis is done to facilitate researchers for selecting the appropriate kernel method for effective graph clustering. The proposed methodology elicits k-step random walk and shortest path kernel have performed best among all graph clustering approaches.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.