Random Walk Diffusion for Efficient Large-Scale Graph Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bernecker, Tobias, Rehawi, Ghalia, Casale, Francesco Paolo, Knauer-Arloth, Janine, Marsico, Annalisa
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910970079608832
author Bernecker, Tobias
Rehawi, Ghalia
Casale, Francesco Paolo
Knauer-Arloth, Janine
Marsico, Annalisa
author_facet Bernecker, Tobias
Rehawi, Ghalia
Casale, Francesco Paolo
Knauer-Arloth, Janine
Marsico, Annalisa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Random Walk Diffusion for Efficient Large-Scale Graph Generation
Bernecker, Tobias
Rehawi, Ghalia
Casale, Francesco Paolo
Knauer-Arloth, Janine
Marsico, Annalisa
Machine Learning
Social and Information Networks
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.
title Random Walk Diffusion for Efficient Large-Scale Graph Generation
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2408.04461