A Vertical Federated Learning Framework for Graph Convolutional Network

TL;DR

This paper introduces FedVGCN, a federated learning framework for graph convolutional networks that preserves data privacy in vertically partitioned settings, enabling secure node classification across isolated data sources.

Contribution

It proposes a novel federated GCN framework that uses homomorphic encryption for privacy-preserving training on vertically partitioned graph data, applicable to existing GCN models.

Findings

Effective on benchmark datasets with GraphSage.

Maintains data privacy during training.

Compatible with existing GCN architectures.

Abstract

Recently, Graph Neural Network (GNN) has achieved remarkable success in various real-world problems on graph data. However in most industries, data exists in the form of isolated islands and the data privacy and security is also an important issue. In this paper, we propose FedVGCN, a federated GCN learning paradigm for privacy-preserving node classification task under data vertically partitioned setting, which can be generalized to existing GCN models. Specifically, we split the computation graph data into two parts. For each iteration of the training process, the two parties transfer intermediate results to each other under homomorphic encryption. We conduct experiments on benchmark data and the results demonstrate the effectiveness of FedVGCN in the case of GraphSage.