Differentially Private Federated Knowledge Graphs Embedding

TL;DR

This paper introduces FKGE, a decentralized, privacy-preserving framework for knowledge graph embedding that enables cross-domain learning without raw data leakage, improving performance on key tasks.

Contribution

It presents a novel federated learning approach for knowledge graph embedding that ensures privacy and scalability across multiple knowledge domains.

Findings

Significant improvements in triple classification accuracy.

Enhanced link prediction performance.

Effective privacy protection in knowledge graph embedding.

Abstract

Knowledge graph embedding plays an important role in knowledge representation, reasoning, and data mining applications. However, for multiple cross-domain knowledge graphs, state-of-the-art embedding models cannot make full use of the data from different knowledge domains while preserving the privacy of exchanged data. In addition, the centralized embedding model may not scale to the extensive real-world knowledge graphs. Therefore, we propose a novel decentralized scalable learning framework, \emph{Federated Knowledge Graphs Embedding} (FKGE), where embeddings from different knowledge graphs can be learnt in an asynchronous and peer-to-peer manner while being privacy-preserving. FKGE exploits adversarial generation between pairs of knowledge graphs to translate identical entities and relations of different domains into near embedding spaces. In order to protect the privacy of the training data, FKGE further implements a privacy-preserving neural network structure to guarantee no raw data leakage. We conduct extensive experiments to evaluate FKGE on 11 knowledge graphs, demonstrating a significant and consistent improvement in model quality with at most 17.85\% and 7.90\% increases in performance on triple classification and link prediction tasks.