AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Interpretable and Differentially Private Predictions

Frederik Harder, Matthias Bauer, Mijung Park

AAAI 2020 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 54 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 a stronger privacy guarantee (lower ε) for LLMLLM · Henan Renmin Hospital Dataaccuracy: 82.0±0.4% -> 79.8±0.4%Hurt
Use a stronger privacy guarantee (ε=0.5 instead of ε=2)DP-LLM · MNISTaccuracy: 94.2±0.4% -> 91.8±0.4%Hurt
Use a stronger privacy guarantee (ε=2 instead of ε=0.5)DP-LLM · Fashion-MNISTaccuracy: 83.2±0.4% -> 80.7±0.6%Hurt
Add data-independent random projections (ablation)DP-LLM · high-dimensional image dataaccuracyImproved
Remove random projections (ablation)DP-LLM · image classificationinterpretabilityImproved
Increase the number of linear maps per class (ablation)DP-LLM · MNIST and Fashion-MNISTaccuracyHurt
Increase the number of linear maps per class (ablation)non-private LLM · MNIST and Fashion-MNISTaccuracyImproved
Increase random-projection output dimensionality (ablation)DP-LLM · MNIST and Fashion-MNISTaccuracyImproved
Increase the number of linear maps per class (ablation)DP-LLM · Henan Renmin Hospital DataaccuracyHurt
Increase the number of linear maps per class (ablation)non-private LLM · Henan Renmin Hospital DataaccuracyHurt
Use stronger privacy (ε < 0.1)DP-LLM · Henan Renmin Hospital DatainterpretabilityHurt

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