A federated graph neural network framework for privacy-preserving personalization.

A federated graph neural network framework for privacy-preserving personalization.
复制标题

用于隐私保护个性化的联合图神经网络框架

DOI:
10.1038/s41467-022-30714-9
复制
发表时间:
2022-06-02
影响因子:
16.6
通讯作者:
--
中科院分区:
综合性期刊1区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

图神经网络(GNN)能够有效地建模高阶交互,并已广泛应用于推荐等各种个性化应用中。然而,主流的个性化方法依赖于全局图上的集中式 GNN 学习,由于用户数据的隐私敏感特性,这种方法存在相当大的隐私风险。在这里,我们提出了一个名为 FedPerGNN 的联合 GNN 框架,用于实现有效且保护隐私的个性化。通过保护隐私的模型更新方法,我们可以基于从本地数据推断出的分散图来协作训练 GNN 模型。为了进一步利用本地交互之外的图信息,我们引入了一种隐私保护图扩展协议,以在隐私保护下合并高阶信息。在不同场景下的六个数据集上进行个性化的实验结果表明,在良好的隐私保护下,FedPerGNN 比最先进的联邦个性化方法的错误率降低了 4.0%~9.6%。 FedPerGNN 提供了一个有希望的方向,以保护隐私的方式挖掘去中心化图数据,以实现负责任的智能个性化。主流的个性化方法依赖于全局图上的集中式图神经网络学习,由于用户数据的隐私敏感特性,这种方法存在相当大的隐私风险。在这里,作者提出了一个联合 GNN 框架,用于有效且保护隐私的个性化。
Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rely on centralized GNN learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, we present a federated GNN framework named FedPerGNN for both effective and privacy-preserving personalization. Through a privacy-preserving model update method, we can collaboratively train GNN models based on decentralized graphs inferred from local data. To further exploit graph information beyond local interactions, we introduce a privacy-preserving graph expansion protocol to incorporate high-order information under privacy protection. Experimental results on six datasets for personalization in different scenarios show that FedPerGNN achieves 4.0% ~ 9.6% lower errors than the state-of-the-art federated personalization methods under good privacy protection. FedPerGNN provides a promising direction to mining decentralized graph data in a privacy-preserving manner for responsible and intelligent personalization. Mainstream personalization methods rely on centralized Graph Neural Network learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, the authors present a federated GNN framework for both effective and privacy-preserving personalization.
DOI: 10.1145/2827872
发表时间: 2016-01-01
影响因子: 3.4
作者:
Harper, F. Maxwell;Konstan, Joseph A.
通讯作者: Konstan, Joseph A.
实现对加密外包数据的个性化搜索并提高效率
DOI: 10.1109/tpds.2015.2506573
发表时间: 2016-09-01
影响因子: 5.3
作者:
Fu, Zhangjie;Ren, Kui;Huang, Fengxiao
通讯作者: Huang, Fengxiao
DOI: 10.1038/s41562-020-0889-7
发表时间: 2020-06-15
影响因子: 29.9
作者:
Lorenz-Spreen, Philipp;Lewandowsky, Stephan;Hertwig, Ralph
通讯作者: Hertwig, Ralph
DOI: 10.1109/tkde.2007.46
发表时间: 2007-03-01
影响因子: 8.9
作者:
Fouss, Francois;Pirotte, Alain;Saerens, Marco
通讯作者: Saerens, Marco
DOI: 10.1109/mis.2020.3014880
发表时间: 2021-09-01
影响因子: 6.4
作者:
Chai, Di;Wang, Leye;Yang, Qiang
通讯作者: Yang, Qiang