A noisy edge-copying generative model for temporal hypergraphs yields analytic asymptotics for degree, edge size, and edge intersection distributions, plus a scalable stochastic EM fitter that matches or beats neural link predictors with only 11 parameters.
Networks be- yond pairwise interactions: Structure and dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Edge Correlations and Link Prediction in Growing Hypergraphs
A noisy edge-copying generative model for temporal hypergraphs yields analytic asymptotics for degree, edge size, and edge intersection distributions, plus a scalable stochastic EM fitter that matches or beats neural link predictors with only 11 parameters.