Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach

TL;DR

This paper introduces a local differential privacy framework for graph neural networks that perturbs node features and labels to protect user privacy while maintaining model utility, using reconstruction techniques for data approximation.

Contribution

It proposes a novel LDP protocol for GNNs that applies randomization to high-dimensional data and develops reconstruction methods to recover features and labels.

Findings

Effective privacy guarantees with low utility loss

Successful data reconstruction from randomized data

Strong performance on real-world datasets

Abstract

Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework that can provide node privacy at the user level, while incurring low utility loss. We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training. Specifically, we investigate the application of randomization mechanisms in high-dimensional feature settings and propose an LDP protocol with strict privacy guarantees. Based on frequency estimation in statistical analysis of randomized data, we develop reconstruction methods to approximate features and labels from perturbed data. We also formulate this learning framework to utilize frequency estimates of graph clusters to supervise the training procedure at a sub-graph level. Extensive experiments on real-world and semi-synthetic datasets demonstrate the validity of our proposed model.