A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy

被引:2
|
作者
Qiu, Yeqing [1 ,2 ]
Huang, Chenyu [1 ]
Wang, Jianzong [1 ]
Huang, Zhangcheng [1 ]
Xiao, Jing [1 ]
机构
[1] Ping An Technol Shenzhen Co Ltd, Shenzhen, Peoples R China
[2] Beijing Jiaotong Univ, Beijing, Peoples R China
关键词
Recommendation system; Federated learning; Subgraph-level federated learning; Graph neural network; Differential privacy;
D O I
10.1007/978-3-031-10989-8_14
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:165 / 177
页数:13
相关论文
共 50 条
  • [1] Subgraph-level federated graph neural network for privacy-preserving recommendation with meta-learning
    Han, Zhaoxing
    Hu, Chengyu
    Li, Tongyaqi
    Qi, Qingqiang
    Tang, Peng
    Guo, Shanqing
    [J]. NEURAL NETWORKS, 2024, 179
  • [2] Personalized and privacy-preserving federated graph neural network
    Liu, Yanjun
    Li, Hongwei
    Hao, Meng
    [J]. FRONTIERS IN PHYSICS, 2024, 12
  • [3] A federated graph neural network framework for privacy-preserving personalization
    Chuhan Wu
    Fangzhao Wu
    Lingjuan Lyu
    Tao Qi
    Yongfeng Huang
    Xing Xie
    [J]. Nature Communications, 13
  • [4] A federated graph neural network framework for privacy-preserving personalization
    Wu, Chuhan
    Wu, Fangzhao
    Lyu, Lingjuan
    Qi, Tao
    Huang, Yongfeng
    Xie, Xing
    [J]. NATURE COMMUNICATIONS, 2022, 13 (01)
  • [5] Privacy-Preserving Recommendation Based on a Shuffled Federated Graph Neural Network
    Liu, Qinbo
    Yang, Lichen
    Liu, Yang
    Deng, Jiaqi
    Wu, Guorui
    [J]. IEEE INTERNET COMPUTING, 2024, 28 (03) : 17 - 24
  • [6] POSEIDON: Privacy-Preserving Federated Neural Network Learning
    Sav, Sinem
    Pyrgelis, Apostolos
    Troncoso-Pastoriza, Juan Ramon
    Froelicher, David
    Bossuat, Jean-Philippe
    Sousa, Joao Sa
    Hubaux, Jean-Pierre
    [J]. 28TH ANNUAL NETWORK AND DISTRIBUTED SYSTEM SECURITY SYMPOSIUM (NDSS 2021), 2021,
  • [7] Privacy-preserving graph convolution network for federated item recommendation
    Hu, Pengqing
    Lin, Zhaohao
    Pan, Weike
    Yang, Qiang
    Peng, Xiaogang
    Ming, Zhong
    [J]. ARTIFICIAL INTELLIGENCE, 2023, 324
  • [8] Privacy-Preserving Federated Graph Neural Network Learning on Non-IID Graph Data
    Zhang, Kainan
    Cai, Zhipeng
    Seo, Daehee
    [J]. Wireless Communications and Mobile Computing, 2023, 2023
  • [9] Privacy-Preserving Robust Federated Learning with Distributed Differential Privacy
    Wang, Fayao
    He, Yuanyuan
    Guo, Yunchuan
    Li, Peizhi
    Wei, Xinyu
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, 2022, : 598 - 605
  • [10] Decentralized Graph Neural Network for Privacy-Preserving Recommendation
    Zheng, Xiaolin
    Wang, Zhongyu
    Chen, Chaochao
    Qian, Jiashu
    Yang, Yao
    [J]. PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023, 2023, : 3494 - 3504