AI Paper Atlas

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

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

NeurIPS 2022 · Federated learning and privacy › Communication-efficient FL · approach: Decentralized peer-to-peer training · 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 OoD samples to cloud data (ID -> ID+OoD)random sampling budget 1000 · Digits averageaccuracy (%): 70.4 -> 62.4Hurt
increase sampling budget with ID+OoD cloud datarandom sampling · Digits averageaccuracy (%): 62.4 -> 68.4Improved
use ECOS instead of random sampling in selective labelingECOS · DomainNet Quickdraw, budget 1000accuracy (%): 77.9 -> 84.3Improved
use K-Center instead of random samplingK-Center · DomainNet Quickdraw, budget 3000accuracy (%): 86.1 -> 60.5Hurt
use ECOS instead of K-Center in selective labelingECOS · Digits SVHN, budget 2000accuracy (%): 65.1 -> 68.7Improved
use ECOS in adaptive model compressionECOS · DomainNet compression, budget 1000avg accuracy (%): 76.4 -> 78.6Improved
use ECOS before private kNN client labelingECOS · Digits client labeling, budget 5000avg accuracy (%): 65.9 -> 69.0Improved
use ECOS before private kNN client labelingECOS · DomainNet client labeling, budget 3000avg accuracy (%): 40.4 -> 43.2Improved
add proximity objective only (no diversity) (ablation)ECOS · DomainNet client labelingavg accuracy (%): 40.4 -> 35.2Hurt
add diversity objective only (no proximity) (ablation)ECOS · DomainNet client labelingavg accuracy (%): 40.4 -> 42.0Improved
combine proximity and diversity (ablation)ECOS · DomainNet client labelingavg accuracy (%): 42.0 -> 43.2Improved
increase compression size R at large budget (e.g. 8000) (ablation)ECOS · Digits ID+OoDID TPRMixed

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