PuSH - Publikationsserver des Helmholtz Zentrums München

Mueller, T.T.* ; Paetzold, J.C. ; Prabhakar, C.* ; Usynin, D.* ; Rueckert, D.* ; Kaissis, G.

Differentially private graph neural networks for whole-graph classification.

IEEE Trans. Pattern Anal. Mach. Intell. 45, 7308-7318 (2023)
Verlagsversion DOI PMC
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
Graph Neural Networks (GNNs) have established themselves as state-of-the-art for many machine learning applications such as the analysis of social and medical networks. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of graphs. In this work, we introduce a framework for differential private graph-level classification. Our method is applicable to graph deep learning on multi-graph datasets and relies on differentially private stochastic gradient descent (DP-SGD). We show results on a variety of datasets and evaluate the impact of different GNN architectures and training hyperparameters on model performance for differentially private graph classification, as well as the scalability of the method on a large medical dataset. Our experiments show that DP-SGD can be applied to graph classification tasks with reasonable utility losses. Furthermore, we apply explainability techniques to assess whether similar representations are learned in the private and non-private settings. Our results can also function as robust baselines for future work in this area.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Training; Privacy; Task analysis; Graph neural networks; Data models; Stochastic processes; Image edge detection; Differential privacy; graph neural networks; Database
ISSN (print) / ISBN 0162-8828
e-ISSN 1939-3539
Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence
Quellenangaben Band: 45, Heft: 6, Seiten: 7308-7318 Artikelnummer: , Supplement: ,
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Verlagsort 10662 Los Vaqueros Circle, Po Box 3014, Los Alamitos, Ca 90720-1314 Usa
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
Institute for Tissue Engineering and Regenerative Medicine (ITERM)