Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation. (arXiv:2203.09553v3 [cs.AI] UPDATED)

Federated learning (FL) can be essential in knowledge representation,
reasoning, and data mining applications over multi-source knowledge graphs
(KGs). A recent study FedE first proposes an FL framework that shares entity
embeddings of KGs across all clients. However, entity embedding sharing from
FedE would incur a severe privacy leakage. Specifically, the known entity
embedding can be used to infer whether a specific relation between two entities
exists in a private client. In this paper, we introduce a novel attack method …

aggregation arxiv embedding federated learning graphs knowledge knowledge graphs privacy