Theory of Graph Neural Networks: Representation and Learning
It provides a theoretical overview for researchers in machine learning, but it is incremental as it summarizes existing results rather than presenting new findings.
This article tackles the problem of understanding the theoretical foundations of Graph Neural Networks (GNNs) by summarizing emerging results on their approximation and learning properties, focusing on representation, generalization, and extrapolation.
Graph Neural Networks (GNNs), neural network architectures targeted to learning representations of graphs, have become a popular learning model for prediction tasks on nodes, graphs and configurations of points, with wide success in practice. This article summarizes a selection of the emerging theoretical results on approximation and learning properties of widely used message passing GNNs and higher-order GNNs, focusing on representation, generalization and extrapolation. Along the way, it summarizes mathematical connections.