Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals

Excerpt

arXiv:2609.39658v1 Announce Type: new Abstract: Diffusion models generate data by reversing a forward corruption process that typically approaches a simple Gaussian prior. Recent work has extended this framework to signals supported on fixed graphs, e.g., road-network traffic and sensor-network measurements. Many graph signals have nonuniform spectral energy, whereas isotropic corruption adds the same conditional noise variance to every graph-frequency mode. Driving all modes to near-zero termin