Privacy-Preserving Graph Neural Network for Node Classification

by   Jun Zhou, et al.
Ant Financial
Zhejiang University
Peking University

Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes. High-performance GNN models always depend on both rich features and complete edge information in graph. However, such information could possibly be isolated by different data holders in practice, which is the so-called data isolation problem. To solve this problem, in this paper, we propose a Privacy-Preserving GNN (PPGNN) learning paradigm for node classification task, which can be generalized to existing GNN models. Specifically, we split the computation graph into two parts. We leave the private data (i.e., features, edges, and labels) related computations on data holders, and delegate the rest of computations to a semi-honest server. We conduct experiments on three benchmarks and the results demonstrate that PPGNN significantly outperforms the GNN models trained on the isolated data and has comparable performance with the traditional GNN trained on the mixed plaintext data.


page 1

page 2

page 3

page 4


A Vertical Federated Learning Framework for Graph Convolutional Network

Recently, Graph Neural Network (GNN) has achieved remarkable success in ...

Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learning

In recent years, the fast rise in number of studies on graph neural netw...

ASFGNN: Automated Separated-Federated Graph Neural Network

Graph Neural Networks (GNNs) have achieved remarkable performance by tak...

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

Deep Neural Networks (DNNs) have achieved remarkable progress in various...

Spatial Graph Coarsening: Weather and Weekday Prediction with London's Bike-Sharing Service using GNN

This study introduced the use of Graph Neural Network (GNN) for predicti...

SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention

With the frequent happening of privacy leakage and the enactment of priv...

A Novel Generalized Artificial Neural Network for Mining Two-Class Datasets

A novel general neural network (GNN) is proposed for two-class data mini...

Please sign up or login with your details

Forgot password? Click here to reset