Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Generator-based Graph Generation via Heat Diffusion

About

Graph generative modelling has become an essential task due to the wide range of applications in chemistry, biology, social networks, and knowledge representation. In this work, we propose a novel framework for generating graphs by adapting the Generator Matching (arXiv:2410.20587) paradigm to graph-structured data. We leverage the graph Laplacian and its associated heat kernel to define a continous-time diffusion on each graph. The Laplacian serves as the infinitesimal generator of this diffusion, and its heat kernel provides a family of conditional perturbations of the initial graph. A neural network is trained to match this generator by minimising a Bregman divergence between the true generator and a learnable surrogate. Once trained, the surrogate generator is used to simulate a time-reversed diffusion process to sample new graph structures. Our framework unifies and generalises existing diffusion-based graph generative models, injecting domain-specific inductive bias via the Laplacian, while retaining the flexibility of neural approximators. Experimental studies demonstrate that our approach captures structural properties of real and synthetic graphs effectively.

Anthony Stephenson, Ian Gallagher, Christopher Nemeth• 2026

Related benchmarks

TaskDatasetResultRank
Graph generationENZYMES
Clustering0.0225
45
Graph generationPlanar--
10
Graph generationPROTEINS
Clustering Coefficient Error0.0465
4
Graph generationDCSBM
Clustering Coefficient0.234
4
Graph generationQM9
Clustering Coefficient0.0834
4
Graph generationSBM
Clustering Coefficient0.0398
4
Showing 6 of 6 rows

Other info

Follow for update