A federated compositional knowledge graph embedding for communication efficiency

Abstract

Knowledge Graph Embedding (KGE), which automatically capture structural information from Knowledge Graphs (KGs), are essential for enhancing various downstream applications, such as recommender systems. To further improve the effectiveness of KGE models, Federated Knowledge Graph Embedding (FKGE) is introduced. It enables privacy-preserving integration of KGs across multiple organizations. However, existing FKGE frameworks require aggregation of a large global KGE model (embeddings). resulting in significant communication overhead, thereby reducing the efficiency and utility of FKGE in practical scenarios. To address this challenge, we propose Federated Compositional Knowledge Graph Embedding (FedComp), which enhances communication efficiency by leveraging the compositional characteristics of KG entities. In FedComp, we design a lightweight global model that represents shareable latent features of entities. These global latent features are composed into personalized KGE models with local embedding generators on the clients, improving both local adaptability and performance. By this, FedComp can significantly reduce the number of parameters that need to be transmitted. Experimental results show that FedComp outperforms state-of-the-art FKGE frameworks on link prediction accuracy, with only around 1.0% communication overhead compared to counterpart frameworks.