A Network Science Perspective of Graph Convolutional Networks: A Survey
Open Access
- 20 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 39083-39122
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.Keywords
All Related Versions
Funding Information
- Australian Research Council (DP19010108)
This publication has 181 references indexed in Scilit:
- Mathematical Formulation of Multilayer NetworksPhysical Review X, 2013
- Identifying Influential Nodes in Large-Scale Directed Networks: The Role of ClusteringPLOS ONE, 2013
- Multiplex PageRankPLOS ONE, 2013
- Potential Theory for Directed NetworksPLOS ONE, 2013
- Hierarchy Measure for Complex NetworksPLOS ONE, 2012
- Degree centrality for semantic abstraction summarization of therapeutic studiesJournal of Biomedical Informatics, 2011
- Using graph theory to analyze biological networksBioData Mining, 2011
- The e-Index, Complementing the h-Index for Excess CitationsPLOS ONE, 2009
- Graphs in molecular biologyBMC Bioinformatics, 2007
- A model of Internet topology usingk-shell decompositionProceedings of the National Academy of Sciences, 2007