Introduction

Abstract

Graphs are a kind of data structure which models a set of objects (nodes) and their relationships (edges). Recently, researches of analyzing graphs with machine learning have received more and more attention because of the great expressive power of graphs, i.e., graphs can be used as denotation of a large number of systems across various areas including social science (social networks) [Hamilton et al., 2017b, Kipf and Welling, 2017], natural science (physical systems [Battaglia et al., 2016, Sanchez et al., 2018] and protein-protein interaction networks [Fout et al., 2017]), knowledge graphs [Hamaguchi et al., 2017] and many other research areas [Khalil et al., 2017]. As a unique non-Euclidean data structure for machine learning, graph draws attention on analyses that focus on node classification, link prediction, and clustering. Graph neural networks (GNNs) are deep learning-based methods that operate on graph domain. Due to its convincing performance and high interpretability, GNN has been a widely applied graph analysis method recently. In the following paragraphs, we will illustrate the fundamental motivations of GNNs.