ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees. (arXiv:2304.08928v1 [cs.LG])

Graph Neural Networks (GNNs) have become a popular tool for learning on
graphs, but their widespread use raises privacy concerns as graph data can
contain personal or sensitive information. Differentially private GNN models
have been recently proposed to preserve privacy while still allowing for
effective learning over graph-structured datasets. However, achieving an ideal
balance between accuracy and privacy in GNNs remains challenging due to the
intrinsic structural connectivity of graphs. In this paper, we propose a new
differentially private GNN …

balance called connectivity data datasets differential privacy graphs information networks neural networks personal popular privacy private sensitive information tool training