At this meeting we discussed A Gentle Introduction to Graph Neural Networks. This article introduces Graph Neural Networks (GNNs) and builds from the basics up to a more complete picture without assuming any prior knowledge of graphs/graph theory. GNNs have already been applied to problems in particle physics and fluid dynamic and may be an interesting avenue to investigate.

Abstract

Graphs are all around us; real world objects are often defined in terms of their connections to other things. A set of objects, and the connections between them, are naturally expressed as a graph. Researchers have developed neural networks that operate on graph data (called graph neural networks, or GNNs) for over a decade. Recent developments have increased their capabilities and expressive power. We are starting to see practical applications in areas such as antibacterial discovery , physics simulations , fake news detection , traffic prediction and recommendation systems.
This article explores and explains modern graph neural networks. We divide this work into four parts. First, we look at what kind of data is most naturally phrased as a graph, and some common examples. Second, we explore what makes graphs different from other types of data, and some of the specialized choices we have to make when using graphs. Third, we build a modern GNN, walking through each of the parts of the model, starting with historic modeling innovations in the field. We move gradually from a bare-bones implementation to a state-of-the-art GNN model. Fourth and finally, we provide a GNN playground where you can play around with a real-word task and dataset to build a stronger intuition of how each component of a GNN model contributes to the predictions it makes.

Article available via distill.pub here. There is also a companion article on Understand Convolutions on Graphs available here.