For large dense weighted SIS networks, prediction of epidemic curves is uniformly stable under trajectory-fitting error, while network reconstruction is provably non-identifiable in the cut norm.
Graphon branching processes and fractional isomorphism
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In their study of the giant component in inhomogeneous random graphs, Bollob\'as, Janson, and Riordan introduced a class of branching processes parametrized by a possibly unbounded graphon. We prove that the tree structures underlying two such branching processes have the same distributions if and only if the corresponding graphons are fractionally isomorphic, a notion introduced by Greb\'ik and Rocha. A different class of branching processes was introduced by Hladk\'y, Nachmias, and Tran in relation to uniform spanning trees in finite graphs approximating a given connected graphon. We prove that that the tree structures of two such branching processes have the same distributions if and only if the corresponding graphons are fractionally isomorphic up to scalar multiple. Combined with a recent result of Archer and Shalev, this implies that if uniform spanning trees of two dense graphs have a similar local structure, they have a similar scaling limit. As a side result we give a characterization of fractional isomorphism for graphs as well as graphons in terms of their connected components.
citation-role summary
citation-polarity summary
fields
q-bio.PE 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Why is it easier to predict the epidemic curve than to reconstruct the underlying contact network?
For large dense weighted SIS networks, prediction of epidemic curves is uniformly stable under trajectory-fitting error, while network reconstruction is provably non-identifiable in the cut norm.