2025
SGRAND: Stochastic Graph Neural Diffusion
ICASSP 2025accepted
In this work, we present Stochastic Graph Neural Diffusion, which approaches deep learning on graphs as a continuous stochastic heat diffusion process. We generalize the Stochastic Heat Equation on the Riemannian manifold to graphs and treat GNNs as a discretization of the Stochastic Heat Conduction…