AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging

Edwige Cyffers, Mathieu Even, Aurélien Bellet, Laurent Massoulié

NeurIPS 2022 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 2 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
add gossip averaging after local noise injection (Muffliato) versus LDPMuffliato · synthetic exponential graph, n=2048pairwise privacy lossImproved
use Erdos-Renyi graph versus exponential graphMuffliato · synthetic graphs, n=2048privacy-utility trade-offNo clear effect
use grid topology versus exponential or Erdos-RenyiMuffliato · synthetic graphs, n=2048privacy-utility trade-offHurt
increase graph distance between nodesMuffliato · Facebook ego graphpairwise privacy lossImproved
use time-varying Erdos-Renyi graphs after each gradient stepMuffliato-GD · UCI Housing logistic regressionprivacy loss uniformity across nodesImproved
increase number of nodes from n=2000 to n=4000Muffliato-GD · UCI Housing logistic regressionprivacy gain over LDPImproved
replace trusted central server aggregation with gossipingMuffliato-GD · UCI Housing logistic regressionaccuracyNo clear effect

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