AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

A Privacy-Friendly Approach to Data Valuation

Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal

NeurIPS 2023 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 0 citations (OpenAlex)

Read the paper

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 DP-TKNN-Shapley instead of DP-KNN-Shapley without subsampling at eps=0.1DP data valuation · Mislabeled detection, 2dPlanesAUROC: 0.49 -> 0.883Improved
Use DP-TKNN-Shapley instead of subsampled DP-KNN-Shapley at eps=0.1DP data valuation · Mislabeled detection, 2dPlanesAUROC: 0.733 -> 0.883Improved
Use DP-TKNN-Shapley instead of subsampled DP-KNN-Shapley at eps=0.1DP data valuation · Noisy detection, CPUAUROC: 0.709 -> 0.805Improved
Use DP-TKNN-Shapley instead of subsampled DP-KNN-Shapley at eps=0.1DP data valuation · Mislabeled detection, PhonemeAUROC: 0.692 -> 0.816Improved
Add subsampling (q=0.01) to DP-KNN-ShapleyDP-KNN-Shapley · Mislabeled detection, 2dPlanes, eps=0.1AUROC: 0.49 -> 0.733Improved
Increase privacy budget eps from 0.1 to 1DP-TKNN-Shapley · Mislabeled detection, 2dPlanesAUROC: 0.883 -> 0.913Improved
Increase privacy budget eps from 0.1 to 1DP-TKNN-Shapley · Mislabeled detection, PhonemeAUROC: 0.816 -> 0.826Improved
Replace KNN-Shapley with TKNN-Shapley (non-private)TKNN-Shapley · Mislabeled detection, CIFAR10AUROC: 0.991 -> 0.957Hurt
Replace KNN-Shapley with TKNN-Shapley (non-private)TKNN-Shapley · Mislabeled detection, PolAUROC: 0.928 -> 0.871Hurt
Replace KNN-Shapley with TKNN-Shapley (non-private)TKNN-Shapley · Mislabeled detection, PhonemeAUROC: 0.873 -> 0.826Hurt
Replace KNN-Shapley with TKNN-Shapley (non-private)TKNN-Shapley · Mislabeled detection, CPUAUROC: 0.932 -> 0.946Improved
Replace KNN-Shapley with TKNN-Shapley (non-private)TKNN-Shapley · 13 mislabeled detection datasetsAUROCNo clear effect

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