Tiago da Silva , Amauri Holanda de Souza Júnior , & Diego Parente Paiva Mesquita
Abstract: Graph neural networks have driven a series of recent developments in, e.g., drug discovery, recommender systems, and social network analysis. At their core, GNNs are designed to extract numerical representations for each node in a graph, recursively combining representations of neighboring nodes. This tutorial paper covers some popular and influential GNN models, and discusses their applications in different disciplines. We hope this work will help popularize GNNs in the local community, and foster scientific advances in machine learning and data science.
Keywords: Graph neural networks, geometric deep learning, graph machine learning.
DOI code: 10.21528/lnlm-vol19-no2-art5
PDF file: vol19-no2-art5.pdf
BibTex file: vol19-no2-art5.bib