Sharp threshold for alignment of graph databases with Gaussian weights - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Sharp threshold for alignment of graph databases with Gaussian weights

Luca Ganassali
  • Fonction : Auteur
  • PersonId : 1077335

Résumé

We study the fundamental limits for reconstruction in weighted graph (or matrix) database alignment. We consider a model of two graphs $G, G',$ where $G$ and $G'$ have correlated Gaussian edge weights, and then $G$ is relabeled according to a random uniform permutation. We prove that there is a sharp information-theoretic threshold for exact recovery of the planted permutation. This threshold is the same as the one obtained for detection in a recent work by Y. Wu, J. Xu and S. Yu: in other words, for Gaussian weighted graph alignment, the problem of reconstruction is not more difficult than that of detection. The study is based on the analysis of the MAP estimator, and proofs rely on proper use of the correlation structure of energies of permutations.
Fichier principal
Vignette du fichier
2010.16295.pdf (584.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03139777 , version 1 (02-11-2021)

Identifiants

Citer

Luca Ganassali. Sharp threshold for alignment of graph databases with Gaussian weights. MSML21 (Mathematical and Scientific Machine Learning), Aug 2021, Lausanne, Switzerland. ⟨hal-03139777⟩
59 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More