HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training
This work addresses privacy concerns in decentralized graph-based machine learning for applications like social networks, though it appears incremental as it builds on existing LDP techniques with a novel synthesis approach.
The paper tackles the problem of training graph neural networks (GNNs) with local differential privacy (LDP) to protect both link and node feature privacy, which often causes significant utility loss in existing methods, and proposes HoGS, a framework that synthesizes graphs using homophily to mitigate this impact, achieving higher accuracy on three real-world datasets compared to baselines.
Graph neural networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks by effectively modeling high-order interactions between nodes. However, training GNNs without protection may leak sensitive personal information in graph data, including links and node features. Local differential privacy (LDP) is an advanced technique for protecting data privacy in decentralized networks. Unfortunately, existing local differentially private GNNs either only preserve link privacy or suffer significant utility loss in the process of preserving link and node feature privacy. In this paper, we propose an effective LDP framework, called HoGS, which trains GNNs with link and feature protection by generating a synthetic graph. Concretely, HoGS first collects the link and feature information of the graph under LDP, and then utilizes the phenomenon of homophily in graph data to reconstruct the graph structure and node features separately, thereby effectively mitigating the negative impact of LDP on the downstream GNN training. We theoretically analyze the privacy guarantee of HoGS and conduct experiments using the generated synthetic graph as input to various state-of-the-art GNN architectures. Experimental results on three real-world datasets show that HoGS significantly outperforms baseline methods in the accuracy of training GNNs.