登录
洞察 - Privacy-Preserving Graph Neural Networks
DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
Proposing a decoupled framework for training GNN models with enhanced privacy-utility trade-off using DP-APPR algorithms.
Edge Private Graph Neural Networks with Singular Value Perturbation: Privacy-Preserving GNN Training Algorithm Eclipse
Eclipse introduces a privacy-preserving GNN training algorithm that perturbs singular values, achieving strong privacy protection on edges while maintaining model utility.
Decoupled Graph Neural Networks with Node-Level Differential Privacy
Achieving node-level differential privacy for training GNNs with enhanced privacy-utility trade-off.
