Graph Embedding VAE: A Permutation Invariant Model of Graph Structure

2019/10/17 by Tony Duan, Duan, Tony, Juho Lee +1
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1910.08057

openalex publication_date 2019/10/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Generative models of graph structure have applications in biology and social sciences. The state of the art is GraphRNN, which decomposes the graph generation process into a series of sequential steps. While effective for modest sizes, it loses its permutation invariance for larger graphs. Instead, we present a permutation invariant latent-variable generative model relying on graph embeddings to encode structure. Using tools from the random graph literature, our model is highly scalable to large graphs with likelihood evaluation and generation in O(|V | + |E|).

Citations

• Auto-Encoding Variational Bayes
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Variational Graph Auto-Encoders
• Neural Message Passing for Quantum Chemistry
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Related

• Permutation Invariant Graph Generation via Score-Based Generative Modeling
• Learning Deep Generative Models of Graphs
• AlignGraph: A Group of Generative Models for Graphs
• Permutation Equivariant Generative Adversarial Networks for Graphs
• GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation