GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation. (arXiv:2203.00949v3 [cs.LG] UPDATED)

In this paper, we study the problem of learning Graph Neural Networks (GNNs)
with Differential Privacy (DP). We propose a novel differentially private GNN
based on Aggregation Perturbation (GAP), which adds stochastic noise to the
GNN's aggregation function to statistically obfuscate the presence of a single
edge (edge-level privacy) or a single node and all its adjacent edges
(node-level privacy). Tailored to the specifics of private learning, GAP's new
architecture is composed of three separate modules: (i) the encoder module, …

gap networks neural networks