Measuring Proximity in Attributed Networks for Community Detection

TL;DR

This paper extends traditional proximity measures to attributed networks by incorporating node attributes, enhancing community detection through spectral clustering, and demonstrating improved insights into network structure.

Contribution

It introduces attribute-aware proximity measures and applies spectral clustering for community detection in attributed networks, which is a novel extension of existing methods.

Findings

Enhanced community detection accuracy in attributed networks

Effective integration of attribute similarity into proximity measures

Successful application to real-world network datasets

Abstract

Proximity measures on graphs have a variety of applications in network analysis, including community detection. Previously they have been mainly studied in the context of networks without attributes. If node attributes are taken into account, however, this can provide more insight into the network structure. In this paper, we extend the definition of some well-studied proximity measures to attributed networks. To account for attributes, several attribute similarity measures are used. Finally, the obtained proximity measures are applied to detect the community structure in some real-world networks using the spectral clustering algorithm.