Synergistic Graph Fusion via Encoder Embedding

Abstract

In this paper, we introduce a method called graph fusion embedding, designed for multi-graph embedding with shared vertex sets. Under the framework of supervised learning, our method exhibits a remarkable and highly desirable synergistic effect: for sufficiently large vertex size, the accuracy of vertex classification consistently benefits from the incorporation of additional graphs. We establish the mathematical foundation for the method, including the asymptotic convergence of the embedding, a sufficient condition for asymptotic optimal classification, and the proof of the synergistic effect for vertex classification. Our comprehensive simulations and real data experiments provide compelling evidence supporting the effectiveness of our proposed method, showcasing the pronounced synergistic effect for multiple graphs from disparate sources.

arXiv comment19 pages main + 11 pages appendix

References in corpus (17)

• The structure and function of complex networks
• Community structure in social and biological networks
• A Comprehensive Survey on Graph Neural Networks
• Natural Scales in Geographical Patterns
• Stochastic blockmodels and community structure in networks
• Structural Properties of the Caenorhabditis elegans Neuronal Network
• Brownian distance covariance
• Spectral clustering and the high-dimensional stochastic blockmodel
• Consistency of community detection in networks under degree-corrected stochastic block models
• The Chi-Square Test of Distance Correlation
• Anomaly Detection in Time Series of Graphs using Fusion of Graph Invariants
• Seeded graph matching for correlated Erdős-Rényi graphs
• One-Hot Graph Encoder Embedding
• The Exact Equivalence of Distance and Kernel Methods for Hypothesis Testing
• Generalized Canonical Correlation Analysis for Classification
• Manifold Matching using Shortest-Path Distance and Joint Neighborhood Selection
• Discovering Communication Pattern Shifts in Large-Scale Labeled Networks using Encoder Embedding and Vertex Dynamics

Cited by in corpus (5)

• Universally Consistent K-Sample Tests via Dependence Measures
• Encoder Embedding for General Graph and Node Classification
• Fast and Scalable Multi-Kernel Encoder Classifier
• Refined Graph Encoder Embedding via Self-Training and Latent Community Recovery
• Efficient Graph Encoder Embedding for Large Sparse Graphs in Python