Your Discrete Graph Diffusion Model is Secretly Memorizing
Discrete graph diffusion models (GDMs) corrupt the graph structure by adding noise independently to nodes and edges under a Markovian noise model. In the unconditional setting without node features, an equivariant denoiser trained on a single graph is able to generate novel graphs and sample-level metrics such as edge overlap and WL kernel similarity find no evidence of memorization. In this…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
