Skip to content

Graph Generation

Geometric Deep Learning

ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation

Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the …

Preprint
Salvatore Romano, Marco Grassia, Pietro Liò, Giuseppe Mangioni
•
Read more
Geometric Deep Learning

Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning

Graph generation is a crucial task in many fields, including network science and bioinformatics, as it enables the creation of synthetic graphs that mimic the properties of …

Preprint
Salvatore Romano, Marco Grassia, Giuseppe Mangioni
•
Read more