AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Private Set Generation with Discriminative Information

Dingfan Chen, Raouf Kerkouche, Mario Fritz

NeurIPS 2022 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 13 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
constrain synthetic samples to a DCGAN generator output (image prior) (ablation)Private Set Generation · MNIST eps=10 spc=10ConvNet test accuracy (%): 94.9 -> 92.2Hurt
add DCGAN generator prior (ablation)Private Set Generation · FashionMNIST eps=10 spc=20ConvNet test accuracy (%): 77.7 -> 70.7Hurt
add DCGAN generator prior with 1 sample per class (ablation)Private Set Generation · MNIST eps=10 spc=1ConvNet test accuracy (%): 81.4 -> 88.2Improved
add DCGAN generator prior with 1 sample per class (ablation)Private Set Generation · FashionMNIST eps=10 spc=1ConvNet test accuracy (%): 66.7 -> 63.0Hurt
increase samples per class from 20 to 50 (ablation)Private Set Generation · MNIST eps=10ConvNet test accuracy (%): 95.6 -> 94.0Hurt
increase samples per class from 20 to 50 (ablation)Private Set Generation · FashionMNIST eps=10ConvNet test accuracy (%): 77.7 -> 71.3Hurt
increase samples per class from 1 to 10 (ablation)Private Set Generation · MNIST eps=10ConvNet test accuracy (%): 81.4 -> 94.9Improved
replace DP generative models with directly optimized private synthetic setDP-Merf · MNIST eps=10ConvNet test accuracy (%): 85.7 -> 95.6Improved
replace DP-Merf with directly optimized private synthetic setDP-Merf · FashionMNIST eps=1ConvNet test accuracy (%): 61.2 -> 70.2Improved
transfer synthetic set from ConvNet to MLP downstream classifierPrivate Set Generation · FashionMNIST eps=10MLP test accuracy (%): 62.2 vs 73.1 for DP-MerfHurt
add differential privacy (eps=10) to set generationPrivate Set Generation · CIFAR-10 spc=20ConvNet test accuracy (%): 52.6 -> 42.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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