When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

Key points

• This has a fundamental consequence for unconditional graph generation without node features: in the large graph limit, any GNN denoiser applied to an E-R graph approximately outputs an E-R graph, making effective denoising difficult.1
• We instead address the root cause by introducing the Latent Sociability Prior (LSP) and a join} diffusion process that co-evolves latent node sociability variables and graph structure, removing edge independence while preserving exchangeability.1
• Unlike existing latent graph diffusion methods, the sociability mechanism requires no complex encoder: its sole role is to guide edge updates and preserve node heterogeneity throughout the trajectory.1
• We validate our approach on multiple graph generation datasets and show that the proposed framework more accurately captures graph distributions than baseline methods without node features.1

Sources (1)

• [1]When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 03:50 PM

  Discrete graph diffusion models corrupt graph structure through independent edge updates with a Markovian noise model.

  This has a fundamental consequence for unconditional graph generation without node features: in the large graph limit, any GNN denoiser applied to an E-R graph approximately outputs an E-R graph, making effective denoising difficult.

Extractive summary: sentences quoted from the sources.