Graph Structure Learning with Privacy Guarantees for Open Graph Data

2025-07-25

AI Summary

Balancing privacy compliance (e.g., GDPR) and data utility in open graph data publishing remains challenging—especially when data providers and consumers are decoupled. Existing privacy-preserving graph data publishing (PPDP) methods often lack rigorous, end-to-end privacy guarantees at the release stage. Method: This paper introduces Gaussian Differential Privacy (GDP) into the graph publishing phase for the first time, proposing a structured noise injection framework. Grounded in theoretical guarantees, it enables unbiased recovery of graph structure and supports discrete graph-valued variables. By integrating graph structure estimation theory with joint privacy–utility optimization, the framework achieves provable privacy protection without compromising analytical fidelity. Contribution/Results: The method significantly outperforms baselines on downstream tasks—including node classification and link prediction—while maintaining high model utility under stringent privacy budgets. It establishes a formally verifiable, practically deployable paradigm for secure, open sharing of graph data.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Ensuring privacy in large-scale open datasets is increasingly challenging under regulations such as the General Data Protection Regulation (GDPR). While differential privacy (DP) provides strong theoretical guarantees, it primarily focuses on noise injection during model training, neglecting privacy preservation at the data publishing stage. Existing privacy-preserving data publishing (PPDP) approaches struggle to balance privacy and utility, particularly when data publishers and users are distinct entities. To address this gap, we focus on the graph recovery problem and propose a novel privacy-preserving estimation framework for open graph data, leveraging Gaussian DP (GDP) with a structured noise-injection mechanism. Unlike traditional methods that perturb gradients or model updates, our approach ensures unbiased graph structure recovery while enforcing DP at the data publishing stage. Moreover, we provide theoretical guarantees on estimation accuracy and extend our method to discrete-variable graphs, a setting often overlooked in DP research. Experimental results in graph learning demonstrate robust performance, offering a viable solution for privacy-conscious graph analysis.

Problem

• Ensuring privacy in open graph data under GDPR regulations
• Balancing privacy and utility in graph data publishing
• Recovering graph structures with differential privacy guarantees

Innovation

• GDPR-compliant graph structure learning
• Gaussian DP with structured noise
• Unbiased recovery for discrete graphs