AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Breaking the Communication-Privacy-Accuracy Trilemma

Wei-Ning Chen, Peter Kairouz, Ayfer Ozgur

NeurIPS 2020 · Federated learning and privacy › Communication-efficient FL · approach: Decentralized peer-to-peer training · 31 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 recursive Hadamard encoding to jointly meet privacy and communication constraintsFrequency estimation · Frequency estimationℓ2 error: RHR achieves \frac{d}{n\min\left\{ e^\varepsilon, \left( e^{\varepsilon} -1 \right)^2, 2^b, d\right\}}Improved
Replace the full communication of HR with RHRFrequency estimation · Truncated normalized Geo(0.8), d=10000, ε=5ℓ1 estimation errorImproved
Use RHR instead of HRFrequency estimation · Uniform and truncated normalized Geo(0.8)ℓ1 estimation errorNo clear effect
Use Subset Selection instead of RHRFrequency estimation · Uniform and truncated normalized Geo(0.8)ℓ1 estimation errorImproved
Concatenate privatization and quantization rather than design them jointlyMean estimation · Mean estimationℓ2 estimation error: d/n -> d^2Hurt
Concatenate Subset Selection and grouping-based quantizationDistribution estimation · Distribution estimationℓ2 error: O\left(\frac{d^2}{n2^b \min\left( e^\epsilon, (e^\epsilon-1)^2 \right)}\right)Hurt

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