Redes neurais aplicadas a grafos: uma abordagem semi-supervisionada

Abstract

In this work, we propose an in-depth analysis of Graph Convolutional Networks, a semi-supervised machine learning method for node classification in graph-structured data. Based on the seminal work proposed by Thomas Kipf and Max Welling, the objective of this work is to evaluate in depth the characteristics, nuances, and particularities of this method. This method is also applied to real data in Python.