A Network Science perspective of Graph Convolutional Networks: A survey

TL;DR

This survey explores the relationship between traditional network science measures and graph convolutional networks (GCNs), proposing a new taxonomy for both and highlighting future research directions in integrating structural and learning-based graph analysis methods.

Contribution

It introduces a novel taxonomy of GCNs based on structural information and connects traditional network measures with modern GCN techniques, bridging two research areas.

Findings

Proposes a new taxonomy for structural measures in network science.

Classifies GCNs based on message aggregation, content, and learning scope.

Draws connections between traditional structural measures and GCNs.

Abstract

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them. Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.