Graph Convolution Networks: A Journey from Start to End
Mohamed Abdel‐Basset, Nour Moustafa, Hossam Hawash, Zahir Tari · 2023
Graph convolutional networks (GCNs) define a type of convolutional neural network that can work directly on graphs and take advantage of their structural information. This chapter debates one of the most well-known families of graph networks, known as GCNs, which is divided into spectral- and spatial graph convolution networks. The chapter first discusses the main differences between the two categories of GCNs. Then, the chapter provides a detailed explanation and implementation of the state-of-the-art algorithms in each category.