AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Graph Neural Networks for Whole-Graph Classification

Tamara T. Mueller, Johannes Christian Paetzold, Chinmay Prabhakar, Dmitrii Usynin, Daniel Rueckert, Georgios A. Kaissis

TPAMI 2022 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 56 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
train with DP-SGD at eps=0.5 instead of SGDGCN · Syntheticaccuracy: 0.934 -> 0.756Hurt
train with DP-SGD at eps=5 instead of SGDGCN · Syntheticaccuracy: 0.934 -> 0.918No clear effect
train with DP-SGD at eps=5 instead of SGDGCN · Fingerprintaccuracy: 0.785 -> 0.794No clear effect
train with DP-SGD at eps=0.5 instead of SGDGCN · Fingerprintaccuracy: 0.785 -> 0.693Hurt
train with DP-SGD at eps=1 instead of SGDGCN · ECGaccuracy: 0.932 -> 0.824Hurt
train with DP-SGD at eps=10 instead of SGDGCN · Molbaceaccuracy: 0.655 -> 0.609Hurt
tighten privacy budget from eps=5 to eps=1GCN · ECGaccuracy: 0.923 -> 0.824Hurt
switch GNN architecture among GCN, GAT, GraphSAGE under DP-SGDDP-SGD training · all datasetsaccuracyNo clear effect
use DP-SGD with GAT instead of SGD on Molbace at eps=20GAT · Molbaceaccuracy: 0.726 -> 0.580Hurt
increase graph size in synthetic data from 10 to 50 nodesGCN DP-SGD · SyntheticaccuracyImproved
tighten privacy: eps=5 vs eps=0.5 on GNNExplainer overlap with non-DP modelGCN DP-SGD · FingerprintIoU(DP, non-DP): 0.765 -> 0.609Hurt

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