HDAGAP: Hierarchical Deep Adaptive Graph Neural Networks Based on Aggregation Perturbation Differential Privacy

Graph Neural Networks (GNNs) have gained increasing popularity in learning node embeddings for graph inference tasks, but their training raises significant privacy concerns. Recent differential privacy GNN models address this issue by continuously adding Gaussian noise to the aggregation functions. While this effectively obscures individual edge information, the noise accumulates with each aggregation, degrading the quality of the final node representations and complicating the trade-off between privacy and accuracy. In this paper, we propose a novel differential privacy GNN, called HDAGAP. We decompose the GNN into a series of hierarchical sub-models and apply aggregation perturbation techniques at each layer during training. Each node then dynamically adjusts the range of its perceived neighboring nodes through an adaptive mechanism based on the actual environment. This allows the model to learn more discriminative node representations from a broader neighborhood, improving performance while reducing privacy costs. To validate our method, we conducted extensive experiments on three node classification benchmark datasets. Results demonstrate that HDAGAP significantly outperforms existing DP-GNNs in terms of the privacy-accuracy trade-off.