Toward Privacy-Aware Efficient Federated Graph Attention Network in Smart Cloud

Jinhao Zhou, Zhou Su*, Yuntao Wang, Yanghe Pan, Qianqian Pan, Lizheng Liu, Jun Wu*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Federated graph attention networks (FGATs), blending federated learning (FL) with graph attention networks (GAT), present a novel paradigm for collaborative, privacy-conscious graph model training in the smart cloud. FGATs leverage distributed attention mechanisms to enhance graph feature prioritization, improving representation learning while preserving data decentralization. Despite their advancements, FGATs face privacy concerns, such as attribute inference. Our study proposes an efficient privacy-preserving FGAT (PFGAT). We devise an improved multiplication triplet (IMT)-based attention mechanism with a hybrid differential privacy (DP) approach. We invent a novel triplet generation method and a hybrid neighbor aggregation algorithm, specifically designed to respect the distinct traits of neighbor nodes, efficiently secures GAT node embeddings. Evaluations on benchmarks such as Cora, Citeseer, and Pubmed demonstrate PFGAT's ability to safeguard privacy without compromising on efficiency or performance.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 9th International Conference on Smart Cloud, SmartCloud 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages19-24
Number of pages6
ISBN (Electronic)9798350389500
DOIs
Publication statusPublished - 2024
Event9th IEEE International Conference on Smart Cloud, SmartCloud 2024 - New York City, United States
Duration: 2024 May 102024 May 12

Publication series

NameProceedings - 2024 IEEE 9th International Conference on Smart Cloud, SmartCloud 2024

Conference

Conference9th IEEE International Conference on Smart Cloud, SmartCloud 2024
Country/TerritoryUnited States
CityNew York City
Period24/5/1024/5/12

Keywords

  • Federated learning
  • attention mechanism
  • differential privacy
  • graph neural network
  • secure computation
  • smart cloud

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Toward Privacy-Aware Efficient Federated Graph Attention Network in Smart Cloud'. Together they form a unique fingerprint.

Cite this