Graph-based clustering under differential privacy - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Graph-based clustering under differential privacy

Résumé

In this paper, we present the first differentially private clustering method for arbitrary-shaped node clusters in a graph. This algorithm takes as input only an approximate Minimum Spanning Tree (MST) T released under weight differential privacy constraints from the graph. Then, the underlying nonconvex clustering partition is successfully recovered from cutting optimal cuts on T . As opposed to existing methods, our algorithm is theoretically well-motivated. Experiments support our theoretical findings.
Fichier principal
Vignette du fichier
arXiv_RafaelPinot.pdf (747.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

cea-04558315 , version 1 (24-04-2024)

Identifiants

  • HAL Id : cea-04558315 , version 1

Citer

Rafaël Pinot, Anne Morvan, Florian Yger, Cedric Gouy-Pailler, Jamal Atif. Graph-based clustering under differential privacy. Plate-Forme Intelligence Artificielle PFIA, Jul 2019, Toulouse, France. ⟨cea-04558315⟩
0 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More