Sparse training of discrete diffusion models for graph generation

Y Qin, C Vignac, P Frossard - arxiv preprint arxiv:2311.02142, 2023 - arxiv.org
Generative graph models struggle to scale due to the need to predict the existence or type of
edges between all node pairs. To address the resulting quadratic complexity, existing …

Graph Generation with -trees

Y Jang, D Kim, S Ahn - arxiv preprint arxiv:2305.19125, 2023 - arxiv.org
Generating graphs from a target distribution is a significant challenge across many domains,
including drug discovery and social network analysis. In this work, we introduce a novel …

A simple and scalable representation for graph generation

Y Jang, S Lee, S Ahn - arxiv preprint arxiv:2312.02230, 2023 - arxiv.org
Recently, there has been a surge of interest in employing neural networks for graph
generation, a fundamental statistical learning problem with critical applications like molecule …

Sparse Training of Discrete Diffusion Models for Graph Generation

QIN Yiming, C Vignac, P Frossard - openreview.net
Generative models for graphs often encounter scalability challenges due to the inherent
need to predict interactions for every node pair. Despite the sparsity often exhibited by real …