Inexact Graph Matching Using Centrality Measures

TL;DR

This paper presents an approximate inexact graph matching method that uses centrality measures to reduce graph size, thereby improving computational efficiency in similarity assessment.

Contribution

It introduces a novel approach combining centrality-based graph reduction with inexact matching, enhancing speed without significantly sacrificing accuracy.

Findings

Reduces running time of inexact graph matching

Demonstrates effectiveness of centrality measures in graph reduction

Maintains acceptable matching quality

Abstract

Graph matching is the process of computing the similarity between two graphs. Depending on the requirement, it can be exact or inexact. Exact graph matching requires a strict correspondence between nodes of two graphs, whereas inexact matching allows some flexibility or tolerance during the graph matching. In this chapter, we describe an approximate inexact graph matching by reducing the size of the graphs using different centrality measures. Experimental evaluation shows that it can reduce running time for inexact graph matching.