GraphMaker: Can Diffusion Models Generate Large Attributed Graphs?

Mufei Li, Eleonora Kreacic, Vamsi K. Potluru, Pan Li

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: graph generation, large attributed graphs, denoising diffusion model, discrete diffusion, graph neural networks

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose GraphMaker, a diffusion model for generating large attributed graphs, along with an evaluation pipeline that trains models on generated graphs and tests them on real graphs. GraphMaker achieves superior performance on real-world datasets.

Abstract: Large-scale graphs with node attributes are fundamental in real-world scenarios, such as social and financial networks. The generation of synthetic graphs that emulate real-world ones is pivotal in graph machine learning, aiding network evolution understanding and data utility preservation when original data cannot be shared. Traditional models for graph generation suffer from limited model capacity. Recent developments in diffusion models have shown promise in merely graph structure generation or the generation of small molecular graphs with attributes. However, their applicability to large attributed graphs remains unaddressed due to challenges in capturing intricate patterns and scalability. This paper introduces GraphMaker, a novel diffusion model tailored for generating large attributed graphs. We study the diffusion models that either couple or decouple graph structure and node attribute generation to address their complex correlation. We also employ node-level conditioning and adopt a minibatch strategy for scalability. We further propose a new evaluation pipeline using models trained on generated synthetic graphs and tested on original graphs to evaluate the quality of synthetic data. Empirical evaluations on real-world datasets showcase GraphMaker's superiority in generating realistic and diverse large-attributed graphs beneficial for downstream tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5919