Differentially Private Graph Classification with GNNs
This addresses privacy concerns in graph-based machine learning applications like social networks and protein interactions, but it is incremental as it adapts existing DP-SGD methods to GNNs.
The paper tackles the problem of training Graph Neural Networks (GNNs) with differential privacy for graph-level classification on sensitive datasets, showing results on synthetic and public datasets and evaluating the impact of architectures and hyperparameters on performance.
Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain privacy-sensitive data. Machine learning with differential privacy is a promising technique to allow deriving insight from sensitive data while offering formal guarantees of privacy protection. However, the differentially private training of GNNs has so far remained under-explored due to the challenges presented by the intrinsic structural connectivity of graphs. In this work, we introduce differential privacy for graph-level classification, one of the key applications of machine learning on graphs. Our method is applicable to deep learning on multi-graph datasets and relies on differentially private stochastic gradient descent (DP-SGD). We show results on a variety of synthetic and public datasets and evaluate the impact of different GNN architectures and training hyperparameters on model performance for differentially private graph classification. Finally, we apply explainability techniques to assess whether similar representations are learned in the private and non-private settings and establish robust baselines for future work in this area.