Differentially Private Graph Neural Network with Importance-Grained Noise Adaption

TL;DR

This paper introduces NAP-GNN, a privacy-preserving graph neural network that adaptively protects nodes based on their importance, improving the privacy-utility trade-off for sensitive graph data.

Contribution

The paper proposes a novel importance-grained privacy mechanism for GNNs, including a node importance estimation and adaptive noise addition, with theoretical privacy guarantees.

Findings

NAP-GNN achieves better privacy-accuracy balance in experiments.

The importance estimation accurately identifies critical nodes.

Adaptive noise adapts to node importance, enhancing utility.

Abstract

Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. However, the existing methods ignore that nodes with different importance may yield diverse privacy demands, which may lead to over-protect some nodes and decrease model utility. In this paper, we study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information. First, we propose a Topology-based Node Importance Estimation (TNIE) method to infer unknown node importance with neighborhood and centrality awareness. Second, an adaptive private aggregation method is proposed to perturb neighborhood aggregation from node-importance-grain. Third, we propose to privately train a graph learning algorithm on perturbed aggregations in adaptive residual connection mode over multi-layers convolution for node-wise tasks. Theoretically analysis shows that NAP-GNN satisfies privacy guarantees. Empirical experiments over real-world graph datasets show that NAP-GNN achieves a better trade-off between privacy and accuracy.