Misclassification Rate and Privacy-Utility Trade-offs in Graph Convolutional Networks via Subsampling Stability
Not on the map. Why?
Abstract (arXiv)
We study differential privacy (DP) in Graph Convolutional Networks (GCNs) through the framework of textitsubsampling stability. We derive upper bounds on the misclassification rate that depend explicitly on the subsampling probability ps. Furthermore, we characterize the textitprivacy--utility trade-off by identifying feasible ranges of ps; if ps is too large, the stability-based privacy condition becomes difficult to satisfy, yielding vacuous guarantees, whereas if it is too small, accuracy deteriorates. Our results provide the first rigorous theoretical framework for understanding subsampling stability in GCNs under DP.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 3 May 2026.
Builds on
13 of 20 references.
References · 13
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2016Deep Learning with Differential Privacycited by 2,682
- 2019Graph Neural Networks for Social Recommendationcited by 711
- 2020Stealing Links from Graph Neural Networkscited by 114
- 2021Membership Inference Attack on Graph Neural Networkscited by 81
- 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
- 2021Node-Level Differentially Private Graph Neural Networkscited by 43
- 2019PAC-Bayes Un-Expected Bernstein Inequalitycited by 36
- 2022Differentially Private Community Detection for Stochastic Block Modelscited by 15
- 2023ProGAP: Progressive Graph Neural Networks with Differential Privacy Guaranteescited by 12
- 2023Training Differentially Private Graph Neural Networks with Random Walk Samplingcited by 5
- 2023Stability of Graph Convolutional Neural Networks through the lens of small perturbation analysiscited by 5
Built on by
Not cited yet.