A Jacobi diffusion on graphon space is discretized into a graph-level generative process that matches the continuous process's first moment exactly and second moment up to a closed-form gap, enabling out-of-scale graph generation.
Springer, 2014
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
Spectral DPPs from Markov diffusion generators deliver variance reduction of order n^{1-1/d_int} and MSE rates n^{-1/2-1/(2d_int)} on compact manifolds and k-NN/ε-graphs.
citing papers explorer
-
DiPhon: Diffusion on Graphons for Scalable Graph Generation
A Jacobi diffusion on graphon space is discretized into a graph-level generative process that matches the continuous process's first moment exactly and second moment up to a closed-form gap, enabling out-of-scale graph generation.
-
Fast determinantal sampling on general spaces and diffusion geometry
Spectral DPPs from Markov diffusion generators deliver variance reduction of order n^{1-1/d_int} and MSE rates n^{-1/2-1/(2d_int)} on compact manifolds and k-NN/ε-graphs.