AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning

Tanguy Marchand, Boris Muzellec, Constance Béguier, Jean Du Terrail, Mathieu Andreux

NeurIPS 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Private federated aggregation · 3 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
replace Brent minimization with exponential search (ExpYJ)Yeo-Johnson fitting · UCI datasets, 108 featuresnumerical stability: -14.53 -> -0.21Improved
YJ preprocessing instead of whitening or log normalization before PCACoxPH · TCGA colorectal cancerC-indexImproved
YJ preprocessing instead of whitening or log normalizationCoxPH · TCGA lung and pancreas cancersC-indexNo clear effect
YJ preprocessing instead of no preprocessing or standardizationlinear regression · synthetic federated data, 200 samplesR2Improved
federated YJ instead of local YJ fitted on one center (ablation)linear regression · synthetic federated dataR2Improved

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