
Computing Vertex Centrality Measures in Massive Real Networks with a Neural Learning Model
Vertex centrality measures are a multipurpose analysis tool, commonly u...
read it

Datadriven Analysis of Complex Networks and their Modelgenerated Counterparts
Datadriven analysis of complex networks has been in the focus of resear...
read it

Approximating Network Centrality Measures Using Node Embedding and Machine Learning
Analyzing and extracting useful information from realworld complex netw...
read it

Neural Networks for Complex Data
Artificial neural networks are simple and efficient machine learning too...
read it

Barron Spaces and the Compositional Function Spaces for Neural Network Models
One of the key issues in the analysis of machine learning models is to i...
read it

A Supervised STDPbased Training Algorithm for Living Neural Networks
Neural networks have shown great potential in many applications like spe...
read it

A Unifying Network Architecture for SemiStructured Deep Distributional Learning
We propose a unifying network architecture for deep distributional learn...
read it
Machine Learning in Network Centrality Measures: Tutorial and Outlook
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 realworld 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 realworld 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.
READ FULL TEXT
Comments
There are no comments yet.