PuSH - Publikationsserver des Helmholtz Zentrums München

Mueller, T.T.* ; Chevli, M.* ; Daigavane, A.* ; Rueckert, D.* ; Kaissis, G.

Differentially private graph neural networks for medical population graphs and the impact of the graph structure.

In: (Proceedings - International Symposium on Biomedical Imaging, 27-30 May 2024, Athen). 2024. DOI: 10.1109/ISBI56570.2024.10635840 (Proceedings - International Symposium on Biomedical Imaging)
DOI
We initiate an empirical investigation of differentially private graph neural networks for medical population graphs. In this context, we examine privacy-utility trade-offs at different privacy levels on both real-world and synthetic datasets and perform auditing through membership inference attacks. Our findings highlight the potential and the challenges of this specific DP application area, which comes with an additional difficulty of graph structure construction that potentially complicates graph deep learning. We find evidence that the underlying graph structure constitutes a potential factor for larger performance gaps by showing a correlation between the degree of graph homophily and the accuracy of the trained model.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Differential Privacy ; Graph Neural Networks ; Medical Population Graphs
ISSN (print) / ISBN 1945-7928
e-ISSN 1945-8452
Konferenztitel Proceedings - International Symposium on Biomedical Imaging
Konferzenzdatum 27-30 May 2024
Konferenzort Athen
Nichtpatentliteratur Publikationen
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)