A Network Science perspective of Graph Convolutional Networks: A survey

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.

References in corpus (83)

• Fast unfolding of communities in large networks
• Community structure in social and biological networks
• An index to quantify an individual's scientific research output
• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• The architecture of complex weighted networks
• Geometric deep learning: going beyond Euclidean data
• Identification of influential spreaders in complex networks
• Multilayer Networks
• The structure and dynamics of multilayer networks
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Temporal Networks
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Subgraph Centrality in Complex Networks
• Influence maximization in complex networks through optimal percolation
• Simplifying Graph Convolutional Networks
• Vital nodes identification in complex networks
• Intensity and coherence of motifs in weighted complex networks
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Mathematical Formulation of Multi-Layer Networks
• Leaders in Social Networks, the Delicious Case
• Clustering in Complex Directed Networks
• New Model of Internet Topology Using k-shell Decomposition
• MEDUSA - New Model of Internet Topology Using k-shell Decomposition
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Effective and Efficient Similarity Index for Link Prediction of Complex Networks
• Spectral redemption: clustering sparse networks
• Complex networks in climate dynamics - Comparing linear and nonlinear network construction methods
• Motifs in Temporal Networks
• Graph Self-Supervised Learning: A Survey
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Centrality in Interconnected Multilayer Networks
• Large-Scale Learnable Graph Convolutional Networks
• Node Classification in Social Networks
• Identifying influential spreaders in complex networks based on gravity formula
• Epidemic threshold in structured scale-free networks
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• The Slashdot Zoo: Mining a Social Network with Negative Edges
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Localization and centrality in networks
• Temporal motifs in time-dependent networks
• Graph Metrics for Temporal Networks
• Maximal planar networks with large clustering coefficient and power-law degree distribution
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• Hierarchy measure for complex networks
• Spreading processes in Multilayer Networks
• Identifying Influential Spreaders by Weighted LeaderRank
• Cycles and clustering in bipartite networks
• Investigating the topology of interacting networks - Theory and application to coupled climate subnetworks
• Multiplex PageRank
• Ranking in evolving complex networks
• The clustering coefficient and community structure of bipartite networks
• Multilayer motif analysis of brain networks
• A Novel Measure of Edge Centrality in Social Networks
• A Survey of Natural Language Generation
• Communicability Betweenness in Complex Networks
• Potential Theory for Directed Networks
• Lobby index in networks
• Higher-order clustering in networks
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• A Survey on Subgraph Counting: Concepts, Algorithms and Applications to Network Motifs and Graphlets
• Learning to Generate Questions by Learning What not to Generate
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
• A degree centrality in multi-layered social network
• Higher order clustering coefficients in Barabasi-Albert networks
• Leveraging local h-index to identify and rank influential spreaders in networks
• Experimental analyses on 2-hop-based and 3-hop-based link prediction algorithms
• Directed Graph Convolutional Network
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Decoupling the Depth and Scope of Graph Neural Networks
• Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
• Nested Graph Neural Networks
• Edge-Featured Graph Attention Network
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Measuring Directed Triadic Closure with Closure Coefficients
• Graph Neural Networks with Local Graph Parameters
• TF-GNN: Graph Neural Networks in TensorFlow
• Clustering as a measure of the local topology of networks
• Heterogeneous Graph Matching Networks
• CogDL: A Comprehensive Library for Graph Deep Learning
• Automorphic Equivalence-aware Graph Neural Network
• Asymmetric Graph Representation Learning