Skip to main navigation Skip to search Skip to main content

Private Spectral Clustering Over Binary Stochastic Block Models

  • Princeton University
  • Nokia

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationISIT 2025 - 2025 IEEE International Symposium on Information Theory, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331543990
DOIs
StatePublished - 2025
Event2025 IEEE International Symposium on Information Theory, ISIT 2025 - Ann Arbor, United States
Duration: Jun 22 2025Jun 27 2025

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
ISSN (Electronic)2157-8117

Conference

Conference2025 IEEE International Symposium on Information Theory, ISIT 2025
Country/TerritoryUnited States
CityAnn Arbor
Period06/22/2506/27/25

Keywords

  • Community Detection
  • Differential Privacy
  • Graphs
  • Perturbation
  • Spectral Clustering
  • Stochastic Block Model

Fingerprint

Dive into the research topics of 'Private Spectral Clustering Over Binary Stochastic Block Models'. Together they form a unique fingerprint.

Cite this