Publication
Generative Diffusion Models on Graphs: Methods and Applications
A survey of graph diffusion models, with applications to molecular and protein modeling.
Cite this work View paper
Citation
Wenqi Fan, Chengyi Liu, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li. (2023). Generative Diffusion Models on Graphs: Methods and Applications. IJCAI 2023.
About this work
This survey reviews diffusion models for graph generation. It covers Score Matching with Langevin Dynamics, Denoising Diffusion Probabilistic Models, and score-based generative models.
The applications focus on molecular and protein modeling. The paper also discusses research directions for diffusion on graph-structured data.