On the Price of Differential Privacy for Spectral Clustering over Stochastic Block Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Koskela, Antti, Seif, Mohamed, Goldsmith, Andrea J.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918014617649152
author Koskela, Antti
Seif, Mohamed
Goldsmith, Andrea J.
author_facet Koskela, Antti
Seif, Mohamed
Goldsmith, Andrea J.
contents We investigate privacy-preserving spectral clustering for community detection within stochastic block models (SBMs). Specifically, we focus on edge differential privacy (DP) and propose private algorithms for community recovery. Our work explores the fundamental trade-offs between the privacy budget and the accurate recovery of community labels. Furthermore, we establish information-theoretic conditions that guarantee the accuracy of our methods, providing theoretical assurances for successful community recovery under edge DP.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05816
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Price of Differential Privacy for Spectral Clustering over Stochastic Block Models
Koskela, Antti
Seif, Mohamed
Goldsmith, Andrea J.
Social and Information Networks
Cryptography and Security
Information Theory
Machine Learning
We investigate privacy-preserving spectral clustering for community detection within stochastic block models (SBMs). Specifically, we focus on edge differential privacy (DP) and propose private algorithms for community recovery. Our work explores the fundamental trade-offs between the privacy budget and the accurate recovery of community labels. Furthermore, we establish information-theoretic conditions that guarantee the accuracy of our methods, providing theoretical assurances for successful community recovery under edge DP.
title On the Price of Differential Privacy for Spectral Clustering over Stochastic Block Models
topic Social and Information Networks
Cryptography and Security
Information Theory
Machine Learning
url https://arxiv.org/abs/2505.05816