Improving Graph Generation by Restricting Graph Bandwidth

TL;DR

This paper introduces a method to improve graph generative models by restricting graph bandwidth, which reduces output space, enhances scalability, and improves generation quality without increasing complexity.

Contribution

We propose a novel bandwidth restriction technique for graph generative models that enhances scalability and quality while maintaining model expressiveness.

Findings

Improved generation efficiency and quality on synthetic and real datasets.

Enhanced reconstruction accuracy with bandwidth restriction.

Compatible with existing autoregressive and one-shot models.

Abstract

Deep graph generative modeling has proven capable of learning the distribution of complex, multi-scale structures characterizing real-world graphs. However, one of the main limitations of existing methods is their large output space, which limits generation scalability and hinders accurate modeling of the underlying distribution. To overcome these limitations, we propose a novel approach that significantly reduces the output space of existing graph generative models. Specifically, starting from the observation that many real-world graphs have low graph bandwidth, we restrict graph bandwidth during training and generation. Our strategy improves both generation scalability and quality without increasing architectural complexity or reducing expressiveness. Our approach is compatible with existing graph generative methods, and we describe its application to both autoregressive and one-shot models. We extensively validate our strategy on synthetic and real datasets, including molecular graphs. Our experiments show that, in addition to improving generation efficiency, our approach consistently improves generation quality and reconstruction accuracy. The implementation is made available.