AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Community Detection for Stochastic Block Models

Mohamed S Mohamed, Dung Nguyen, Anil Vullikanti, Ravi Tandon

ICML 2022 · Federated learning and privacy › Differential privacy · approach: Differentially private clustering · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use MLE-based stability rather than graph perturbation with RR + SDPPrivate community detection · Synthetic SBM, r=2 and r=3error probabilityImproved
Use SDP-stability rather than RR + SDPPrivate community detection · Political Blogosphereerror probabilityImproved
Use SDP-stability rather than RR + SDPPrivate community detection · Zachary's Karate Cluberror probabilityMixed
Increase the separation between a and bPrivate community detection mechanisms · Synthetic SBMerror probabilityImproved
Increase εSDP-stability and RR + SDP · Synthetic SBM, r=2error probabilityImproved
Use RR + SDP instead of RR-SpectralRandomized-response recovery · Synthetic SBM, r=2error probabilityImproved
Use finite ε with stability-based mechanisms rather than requiring ε to grow with nStability-based community recovery · Synthetic SBMexact recoveryImproved
Use SDP-stability rather than RR + SDPPrivate community detection · Synthetic SBM, r=3error probabilityImproved
Use RR + SDP rather than RR-SpectralRandomized-response recovery · Synthetic SBM, r=2computational complexityHurt
Use pure-DP sampling mechanisms rather than stability-based mechanismsPrivate community recovery · SBM exact recoveryrecovery thresholdHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy