CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs

Abstract

Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN\_D and CenGCN\_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines.

16 pages, 8 figures

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• DeepWalk: Online Learning of Social Representations
• Power-law distributions in empirical data
• Power laws, Pareto distributions and Zipf's law
• Maps of random walks on complex networks reveal community structure
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Learning: A Survey
• Random Walks: A Review of Algorithms and Applications
• MODEL: Motif-based Deep Feature Learning for Link Prediction
• The Interplay Between Dynamics and Networks: Centrality, Communities, and Cheeger Inequality
• The Gene of Scientific Success
• Spectral Clustering with Epidemic Diffusion
• Graph Filters and the Z-Laplacian
• Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
• Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining

Cited by in corpus (3)

• Deep Outdated Fact Detection in Knowledge Graphs
• Balanced Graph Structure Information for Brain Disease Detection
• Graph Size-imbalanced Learning with Energy-guided Structural Smoothing