A framework for differentially-private knowledge graph embeddings

Han, Xiaolin; Dell’Aglio, Daniele; Grubenmann, Tobias; Cheng, Reynold; Bernstein, Abraham

Abstract

Knowledge graph (KG) embedding methods are at the basis of many KG-based data mining tasks, such as link prediction and node clustering. However, graphs may contain confidential information about people or organizations, which may be leaked via embeddings. Research recently studied how to apply differential privacy to a number of graphs (and KG) analyses, but embedding methods have not been considered so far. This study moves a step toward filling such a gap, by proposing the Differential Private Knowledge Graph Embedding (DPKGE) framework.

DPKGE extends existing KG embedding methods (e.g., TransE, TransM, RESCAL, and DistMult) and processes KGs containing both confidential and unrestricted statements. The resulting embeddings protect the presence of any of the former statements in the embedding space using differential privacy. Our experiments identify the cases where DPKGE produces useful embeddings, by analyzing the training process and tasks executed on top of the resulting embeddings.

Citation

Han, X., Dell’Aglio, D., Grubenmann, T., Cheng, R., & Bernstein, A. (2022). A framework for differentially-private knowledge graph embeddings. Journal of Web Semantics, 72, Article 100696. https://doi.org/10.1016/j.websem.2021.100696

• Journal Article Type: Article
• Acceptance Date: Dec 15, 2021
• Online Publication Date: Dec 24, 2021
• Publication Date: 2022-04
• Deposit Date: Jun 3, 2023
• Journal: Journal of Web Semantics
• Print ISSN: 1570-8268
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 72
• Article Number: 100696
• DOI: https://doi.org/10.1016/j.websem.2021.100696