Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders

Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf, Ke Li

Keywords: Graph Generative Model, Node-Level Properties, Graph-Level Properties. Graph Variational Auto-Encoder

Abstract:

Generative models for graph data are an important research topic in machine learning. Graph data comprise two levels that are typically analyzed separately: node-level properties such as the existence of a link between a pair of nodes, and global aggregate graph-level statistics, such as motif counts.
This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics, as mutually reinforcing sources of information. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. We utilize the micro-macro objective to improve graph generation with a GraphVAE, a well-established model based on graph-level latent variables, that provides fast training and generation time for medium-sized graphs. Our experiments show that adding micro-macro modeling to the GraphVAE model improves graph quality scores up to 2 orders of magnitude on five benchmark datasets, while maintaining the GraphVAE generation speed advantage.

TL;DR: This paper proposes a new graph generative framework that jointly models node and graph level properties as mutually reinforcing sources of information, and applies the framework to improve graph generation with a GraphVAE.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.16844/code)