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

TL;DR

This paper introduces a multi-level graph modeling framework that jointly captures node-level and graph-level features, significantly enhancing graph generation quality while maintaining efficiency.

Contribution

It proposes a novel micro-macro training objective for graph variational auto-encoders, improving graph generation quality by integrating node and graph-level information.

Findings

Graph quality scores improved up to 2 orders of magnitude.

The method maintains fast training and generation times.

Effective on five benchmark datasets.

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.