TY - GEN
T1 - Private Spectral Clustering Over Binary Stochastic Block Models
AU - Seif, Mohamed
AU - Koskela, Antti
AU - Goldsmith, Andrea J.
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
KW - Community Detection
KW - Differential Privacy
KW - Graphs
KW - Perturbation
KW - Spectral Clustering
KW - Stochastic Block Model
UR - https://www.scopus.com/pages/publications/105022015648
U2 - 10.1109/ISIT63088.2025.11195399
DO - 10.1109/ISIT63088.2025.11195399
M3 - Conference contribution
AN - SCOPUS:105022015648
T3 - IEEE International Symposium on Information Theory - Proceedings
BT - ISIT 2025 - 2025 IEEE International Symposium on Information Theory, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE International Symposium on Information Theory, ISIT 2025
Y2 - 22 June 2025 through 27 June 2025
ER -