ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
Open Access
- 4 March 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 596-605
Abstract
Graph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their widespread use raises privacy concerns as graph data can contain personal or sensitive information. Differentially private GNN models have been recently proposed to preserve privacy while still allowing for effective learning over graph-structured datasets. However, achieving an ideal balance between accuracy and privacy in GNNs remains challenging due to the intrinsic structural connectivity of graphs. In this paper, we propose a new differentially private GNN called ProGAP that uses a progressive training scheme to improve such accuracy-privacy trade-offs. Combined with the aggregation perturbation technique to ensure differential privacy, ProGAP splits a GNN into a sequence of overlapping submodels that are trained progressively, expanding from the first submodel to the complete model. Specifically, each submodel is trained over the privately aggregated node embeddings learned and cached by the previous submodels, leading to an increased expressive power compared to previous approaches while limiting the incurred privacy costs. We formally prove that ProGAP ensures edge-level and node-level privacy guarantees for both training and inference stages, and evaluate its performance on benchmark graph datasets. Experimental results demonstrate that ProGAP can achieve up to 5-10% higher accuracy than existing state-of-the-art differentially private GNNs. Our code is available at https://github.com/sisaman/ProGAP.Keywords
All Related Versions
Funding Information
- European Commission (951911)
This publication has 23 references indexed in Scilit:
- Towards Private Learning on Decentralized Graphs With Local Differential PrivacyIEEE Transactions on Information Forensics and Security, 2022
- Graph neural network for traffic forecasting: A surveyExpert Systems with Applications, 2022
- LINKTELLER: Recovering Private Edges from Graph Neural Networks via Influence Analysis2022
- Membership Inference Attack on Graph Neural Networks2021
- ObjectGraphs: Using Objects and a Graph Convolutional Network for the Bottom-up Recognition and Explanation of Events in Video2021
- Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning2021
- Graph Neural Networks for COVID-19 Drug Discovery2020
- Cascade EF-GAN: Progressive Facial Expression Editing With Local Focuses2020
- A Fully Progressive Approach to Single-Image Super-Resolution2018
- Differentially private optimization algorithms for deep neural networks2017