Personalized Federated Knowledge Graph Embedding with Client-Wise Relation Graph

TL;DR

This paper introduces PFedEG, a personalized federated knowledge graph embedding method that uses client-wise relation graphs to enhance embedding quality by considering semantic relevance among clients, outperforming existing approaches.

Contribution

The paper proposes a novel personalized federated KG embedding approach utilizing client-wise relation graphs to better capture semantic disparities among clients.

Findings

PFedEG outperforms state-of-the-art models on four benchmark datasets.

The method effectively learns personalized embeddings by leveraging client affinity.

Experimental results demonstrate improved embedding quality and relevance.

Abstract

Federated Knowledge Graph Embedding (FKGE) has recently garnered considerable interest due to its capacity to extract expressive representations from distributed knowledge graphs, while concurrently safeguarding the privacy of individual clients. Existing FKGE methods typically harness the arithmetic mean of entity embeddings from all clients as the global supplementary knowledge, and learn a replica of global consensus entities embeddings for each client. However, these methods usually neglect the inherent semantic disparities among distinct clients. This oversight not only results in the globally shared complementary knowledge being inundated with too much noise when tailored to a specific client, but also instigates a discrepancy between local and global optimization objectives. Consequently, the quality of the learned embeddings is compromised. To address this, we propose Personalized Federated knowledge graph Embedding with client-wise relation Graph (PFedEG), a novel approach that employs a client-wise relation graph to learn personalized embeddings by discerning the semantic relevance of embeddings from other clients. Specifically, PFedEG learns personalized supplementary knowledge for each client by amalgamating entity embedding from its neighboring clients based on their "affinity" on the client-wise relation graph. Each client then conducts personalized embedding learning based on its local triples and personalized supplementary knowledge. We conduct extensive experiments on four benchmark datasets to evaluate our method against state-of-the-art models and results demonstrate the superiority of our method.