University of Limerick
Browse
- No file added yet -

Complex knowledge graph embeddings based on convolution and translation

Download (1.85 MB)
journal contribution
posted on 2023-07-18, 07:33 authored by Lin-Shi, Zhao Yang, Zhanlin Ji, Ivan GanchevIvan Ganchev

Link prediction involves the use of entities and relations that already exist in a knowledge graph to reason about missing entities or relations. Different approaches have been proposed to date for performing this task. This paper proposes a combined use of the translation-based approach with the Convolutional Neural Network (CNN)-based approach, resulting in a novel model, called ConCMH. In the proposed model, first, entities and relations are embedded into the complex space, followed by a vector multiplication of entity embeddings and relational embeddings and taking the real part of the results to generate a feature matrix of their interaction. Next, a 2D convolution is used to extract features from this matrix and generate feature maps. Finally, the feature vectors are transformed into predicted entity embeddings by obtaining the inner product of the feature mapping and the entity embedding matrix. The proposed ConCMH model is compared against state-of-the-art models on the four most commonly used benchmark datasets and the obtained experimental results confirm its superiority in the majority of cases. 

History

Publication

Mathematics11(12), 2627

Publisher

MDPI

Other Funding information

National Key Research and Development Program of China Science and Education for Smart Growth Operational Program (2014–2020) and co-financed by the European Union through the European Structural and Investment funds.

Department or School

  • Electronic & Computer Engineering

Usage metrics

    University of Limerick

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC