论文标题
通过差异隐私
A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy
论文作者
论文摘要
目前，联邦图神经网络（GNN）由于其现实中广泛的应用而没有违反隐私法规而引起了很多关注。在所有保护隐私的技术中，差异隐私（DP）是最有希望的，因为它的有效性和轻度计算开销。但是，基于DP的联合GNN尚未得到很好的研究，尤其是在子图级环境中，例如推荐系统的情况。最大的挑战是如何同时保证隐私并解决非独立和相同分布的（非IID）数据。在本文中，我们提出了基于DP的联合GNN DP-FEDREC，以填补空白。利用私有集合交叉点（PSI）来扩展每个客户端的本地图，从而解决了非IID问题。最重要的是，DP不仅应用于权重，而且应用于PSI相交图的边缘，以完全保护客户的隐私。评估表明，DP-FEDREC可以通过图表扩展实现更好的性能，而DP仅引入了很少的计算开销。
Currently, the federated graph neural network (GNN) has attracted a lot of attention due to its wide applications in reality without violating the privacy regulations. Among all the privacy-preserving technologies, the differential privacy (DP) is the most promising one due to its effectiveness and light computational overhead. However, the DP-based federated GNN has not been well investigated, especially in the sub-graph-level setting, such as the scenario of recommendation system. The biggest challenge is how to guarantee the privacy and solve the non independent and identically distributed (non-IID) data in federated GNN simultaneously. In this paper, we propose DP-FedRec, a DP-based federated GNN to fill the gap. Private Set Intersection (PSI) is leveraged to extend the local graph for each client, and thus solve the non-IID problem. Most importantly, DP is applied not only on the weights but also on the edges of the intersection graph from PSI to fully protect the privacy of clients. The evaluation demonstrates DP-FedRec achieves better performance with the graph extension and DP only introduces little computations overhead.
