Score: 0

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

Published: May 9, 2025 | arXiv ID: 2505.05816v1

By: Antti Koskela, Mohamed Seif, Andrea J. Goldsmith

Potential Business Impact:

Finds hidden groups in data without sharing secrets.

Business Areas:
Privacy Privacy and Security

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.

Page Count
13 pages

Category
Computer Science:
Social and Information Networks