HEDGE generates hypergraphs via a linear-Gaussian forward diffusion on incidence matrices with a hypergraph-specific heat operator, then learns a permutation-equivariant reverse drift to sample from the Gaussian base.
Hence Erev = 0, the stability term in (32) vanishes, and only theO(∆t 1/2)Euler–Maruyama term remains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hypergraph Generation via Structured Stochastic Diffusion
HEDGE generates hypergraphs via a linear-Gaussian forward diffusion on incidence matrices with a hypergraph-specific heat operator, then learns a permutation-equivariant reverse drift to sample from the Gaussian base.