Autor: Willian Borges de Lemos (Currículo Lattes)
Resumo
The exponential growth of data has presented both opportunities and challenges for organizations and individuals seeking to extract meaningful insights and patterns. In recent years, the field of complex network analysis has gained increasing attention as a solution to identifying patterns and structures in graphs. Graph embedding is a necessary step to bridge the gap between graph data and machine learning algorithms, allowing for the efficient processing and analysis of graph structures. However, the field of graph embedding remains fragmented, with a lack of a consensual theoretical understanding and a unified framework to describe and compare different techniques. This work aims to address these issues by providing a overview of the current state of the art in graph embedding and its influence on complex network analysis. The paper develops a unified framework for describing and comparing various graph embedding techniques, highlighting the strengths and weaknesses of each approach on common factors.
Palavras-chave: Deep Learning; Graph Embedding; Graph Neural Networks; Matrix Factorization