Go to ICLR 2025 Conference homepageDP-GPL: Differentially Private Graph Prompt Learning
Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by advances in language and vision models. Here, a GNN is pre-trained on public data and then adapted to sensitive tasks using lightweight graph prompts. However, using prompts from sensitive data poses privacy risks. In this work, we are the first to investigate these risks in graph prompts by instantiating a membership inference attack that reveals significant privacy leakage. We also find that the standard privacy method, DP-SGD, fails to provide practical privacy-utility trade-offs in graph prompt learning, likely due to the small number of sensitive data points used to learn the prompts. As a solution, we propose two algorithms, DP-GPL and DP-GPL+W, for differentially private graph prompt learning based on the PATE framework, that generate a graph prompt with differential privacy guarantees. Our evaluation across various graph prompt learning methods, GNN architectures, and pre-training strategies demonstrates that our algorithms achieve high utility at strong privacy, effectively mitigating privacy concerns while preserving the powerful capabilities of prompted GNNs.