Hierarchical Discrete Flow Matching for Graph Generation

TL;DR

This paper introduces a hierarchical discrete flow matching framework for graph generation that reduces computational costs and denoising iterations, leading to faster and more effective graph modeling.

Contribution

It proposes a novel hierarchical approach with discrete flow matching to improve efficiency and quality in graph generation tasks.

Findings

More effective at capturing graph distributions.

Substantially reduces generation time.

Requires fewer function evaluations during generation.

Abstract

Denoising-based models, including diffusion and flow matching, have led to substantial advances in graph generation. Despite this progress, such models remain constrained by two fundamental limitations: a computational cost that scales quadratically with the number of nodes and a large number of function evaluations required during generation. In this work, we introduce a novel hierarchical generative framework that reduces the number of node pairs that must be evaluated and adopts discrete flow matching to significantly decrease the number of denoising iterations. We empirically demonstrate that our approach more effectively captures graph distributions while substantially reducing generation time.