For the past few days, I am trying to learn graph convolutional networks. I saw some of the lectures on youtube. But I can not able to get any clear concept of how those networks are trained. I have a vague understanding of how to perform convolution, but I can not understand how we train them. I want a solid mathematical understanding of graph convolutional networks. So, can anyone please suggest me how to start learning graph convolutional network from start to expert level?
I believe Graph Representation Learning book by William L. Hamilton is a great resource to start
There is also the proto-book Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (2021), written by some of the experts on the topic. The book does not focus only on graphs and graph neural networks (GNNs), but also covers manifolds, geodesics, and other mathematical concepts related to geometric deep learning and other GDL models.