AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu

ICLR 2021 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 25 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 isotropic perturbation of the full gradient with embedding and residual perturbationGP · CIFAR-10 test, ε=8accuracy (%): +18.5%Improved
replace isotropic perturbation of the full gradient with embedding and residual perturbationGP · SVHN test, ε=8accuracy (%): +3.5Improved
replace isotropic perturbation of the full gradient with embedding and residual perturbationGP · MNIST test, ε=8accuracy (%): +1.2Improved
add perturbation and release of the residual gradient (ablation)B-GEP · CIFAR-10 test, ε=8accuracy (%): 63.0 -> 74.9Improved
add perturbation and release of the residual gradient (ablation)B-GEP · SVHN test, ε=8accuracy (%): 92.3 -> 95.1Improved
add perturbation and release of the residual gradient (ablation)B-GEP · CIFAR-10 validation, ε=0.1, pretrained featuresaccuracy (%): 91.0 -> 90.9No clear effect
use randomly labeled rather than correctly labeled CIFAR10 auxiliary samples (ablation)GEP · CIFAR-10 test, (8,10^{-5})-DPaccuracy (%): 72.9 -> 75.1Improved
use randomly labeled CIFAR100 rather than randomly labeled CIFAR10 auxiliary samples (ablation)GEP · CIFAR-10 test, (8,10^{-5})-DPaccuracy (%): 75.1 -> 74.7No clear effect
increase anchor-gradient count from m=1000 to m=4000 (ablation)GEP · CIFAR-10 test, (8,10^{-5})-DPaccuracy (%): 74.6 -> 75.2Improved

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