A matrix shuffling mechanism for edge-differentially private spectral clustering achieves Õ(1/n) misclassification error via privacy amplification and a unified Davis-Kahan plus margin analysis, outperforming Analyze Gauss and noisy power iteration.
Spectral methods for data science: A statistical perspective.Foundations and Trends®in Machine Learning, 14(5):566–806, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Differentially Private Spectral Graph Clustering: Balancing Privacy, Accuracy, and Efficiency
A matrix shuffling mechanism for edge-differentially private spectral clustering achieves Õ(1/n) misclassification error via privacy amplification and a unified Davis-Kahan plus margin analysis, outperforming Analyze Gauss and noisy power iteration.