<ul><li>Implementing differential privacy in relational learning is important for protecting the privacy of individual entities in sensitive domains.</li><li>Differential Privacy (DP) provides a structured approach to quantify privacy risks, with DP-SGD being commonly used for private model training.</li><li>Challenges in applying DP-SGD to relational learning include high sensitivity due to entities participating in multiple relations and complex sampling procedures.</li><li>This work introduces a framework for relational learning with formal entity-level DP guarantees, including sensitivity analysis, adaptive gradient clipping, and privacy amplification for coupled sampling procedures.</li></ul>

Differentially Private Relational Learning with Entity-level Privacy Guarantees

Discover more