FedE: Embedding Knowledge Graphs in Federated Setting

2020/10/24 by Mingyang Chen, Chen, Mingyang, Wen Zhang +7 · 6 citations
Computer Science · Decision Sciences · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #Data Quality and Management #FOS: Computer and information sciences #Privacy-Preserving Technologies in Data #cs.CL

paper · pdf · doi:10.48550/arxiv.2010.12882

arxiv created 2020/10/24 · openalex publication_date 2020/10/24 · arxiv updated 2020/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Knowledge graphs (KGs) consisting of triples are always incomplete, so it's important to do Knowledge Graph Completion (KGC) by predicting missing triples. Multi-Source KG is a common situation in real KG applications which can be viewed as a set of related individual KGs where different KGs contains relations of different aspects of entities. It's intuitive that, for each individual KG, its completion could be greatly contributed by the triples defined and labeled in other ones. However, because of the data privacy and sensitivity, a set of relevant knowledge graphs cannot complement each other's KGC by just collecting data from different knowledge graphs together. Therefore, in this paper, we introduce federated setting to keep their privacy without triple transferring between KGs and apply it in embedding knowledge graph, a typical method which have proven effective for KGC in the past decade. We propose a Federated Knowledge Graph Embedding framework FedE, focusing on learning knowledge graph embeddings by aggregating locally-computed updates. Finally, we conduct extensive experiments on datasets derived from KGE benchmark datasets and results show the effectiveness of our proposed FedE.

Citations

• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Cited by

• Rethinking Knowledge Distillation in Collaborative Machine Learning: Memory, Knowledge, and Their Interactions
• A Vertical Federated Learning Framework for Graph Convolutional Network
• S2FGL: Spatial Spectral Federated Graph Learning
• Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion
• iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs

Related

• Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization
• FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion
• Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
• Personalized Federated Knowledge Graph Embedding with Client-Wise Relation Graph
• Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation