Decentralized Graph Neural Network for Privacy-Preserving Recommendation

TL;DR

This paper introduces DGREC, a decentralized GNN framework that enhances privacy-preserving recommendations by combining local graph construction, gradient calculation, and a differential privacy mechanism, outperforming existing methods.

Contribution

The paper presents a novel decentralized GNN architecture with a secure gradient-sharing mechanism that improves privacy and communication efficiency in recommendation systems.

Findings

DGREC outperforms existing methods on public datasets.

The secure gradient-sharing mechanism ensures strong privacy guarantees.

Extensive experiments validate the framework's effectiveness.

Abstract

Building a graph neural network (GNN)-based recommender system without violating user privacy proves challenging. Existing methods can be divided into federated GNNs and decentralized GNNs. But both methods have undesirable effects, i.e., low communication efficiency and privacy leakage. This paper proposes DGREC, a novel decentralized GNN for privacy-preserving recommendations, where users can choose to publicize their interactions. It includes three stages, i.e., graph construction, local gradient calculation, and global gradient passing. The first stage builds a local inner-item hypergraph for each user and a global inter-user graph. The second stage models user preference and calculates gradients on each local device. The third stage designs a local differential privacy mechanism named secure gradient-sharing, which proves strong privacy-preserving of users' private data. We conduct extensive experiments on three public datasets to validate the consistent superiority of our framework.