Machine Learning in Network Centrality Measures: Tutorial and Outlook

TL;DR

This paper presents a tutorial on applying neural network algorithms to approximate network centrality measures, significantly reducing computational costs and enabling analysis of large complex networks.

Contribution

It introduces a general methodology for using neural networks to efficiently approximate centrality metrics in complex networks of any size.

Findings

Neural network regression models accurately approximate centrality metrics.

The proposed approach reduces computation time compared to traditional algorithms.

Methodology is adaptable to various complex network models.

Abstract

Complex networks are ubiquitous to several Computer Science domains. Centrality measures are an important analysis mechanism to uncover vital elements of complex networks. However, these metrics have high computational costs and requirements that hinder their applications in large real-world networks. In this tutorial, we explain how the use of neural network learning algorithms can render the application of the metrics in complex networks of arbitrary size. Moreover, the tutorial describes how to identify the best configuration for neural network training and learning such for tasks, besides presenting an easy way to generate and acquire training data. We do so by means of a general methodology, using complex network models adaptable to any application. We show that a regression model generated by the neural network successfully approximates the metric values and therefore are a robust, effective alternative in real-world applications. The methodology and proposed machine learning model use only a fraction of time with respect to other approximation algorithms, which is crucial in complex network applications.