Hyperbolic Geometric Latent Diffusion Model for Graph Generation

arXiv:2405.03188v1 Announce Type: new
Abstract: Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make …

abstract application arxiv community complexity computational computer computer vision cs.lg diffusion diffusion model diffusion models efficiency graph natural them training type vision