Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding. (arXiv:2304.02932v1 [cs.CR])

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts
expressive representation from knowledge graph (KG) to facilitate diverse
downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from
distributed KGs held among clients while avoiding exchanging clients' sensitive
raw KGs, which can still suffer from privacy threats as evidenced in other
federated model trainings (e.g., neural networks). However, quantifying and
defending against such privacy threats remain unexplored for FKGE which
possesses unique properties not shared by previously studied models. …

clients distributed emerging knowledge knowledge graph networks neural networks privacy representation threats trainings trains