Random Walk Diffusion for Efficient Large-Scale Graph Generation

TL;DR

This paper introduces ARROW-Diff, a novel random walk diffusion method that efficiently generates large-scale graphs, outperforming existing methods in speed and quality by combining random walk sampling with graph pruning.

Contribution

The paper presents ARROW-Diff, a scalable diffusion approach for large graph generation that integrates random walk sampling and pruning, improving efficiency and graph quality.

Findings

ARROW-Diff scales efficiently to large graphs.

It surpasses baseline methods in generation speed.

It produces high-quality graphs with better statistics.

Abstract

Graph generation addresses the problem of generating new graphs that have a data distribution similar to real-world graphs. While previous diffusion-based graph generation methods have shown promising results, they often struggle to scale to large graphs. In this work, we propose ARROW-Diff (AutoRegressive RandOm Walk Diffusion), a novel random walk-based diffusion approach for efficient large-scale graph generation. Our method encompasses two components in an iterative process of random walk sampling and graph pruning. We demonstrate that ARROW-Diff can scale to large graphs efficiently, surpassing other baseline methods in terms of both generation time and multiple graph statistics, reflecting the high quality of the generated graphs.