Federated Knowledge Graphs Embedding [article]

Hao Peng, Haoran Li, Yangqiu Song, Vincent Zheng, Jianxin Li
2021 arXiv   pre-print
In this paper, we propose a novel decentralized scalable learning framework, 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
more » ... nts 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.
arXiv:2105.07615v1 fatcat:il5oopbv65cuzhtyk4ciyqr74u