arXiv (Cornell University) · 2022 · 11 citations · 0 references
ComputingComputer ScienceKnowledge NetworksKnowledge RepresentationNatural Language ProcessingGraph-based LearningKnowledge ExtractionKnowledge GraphsKnowledge ModelingRelation ExtractionBenchmark DatasetsGraph EmbeddingsGraph-based Knowledge RepresentationKnowledge Graph EmbeddingsKnowledge Graph RepresentationKnowledge Graph Representation LearningKnowledge Graph Scalability
Translation-based knowledge graph embedding has been one of the most important branches for knowledge representation learning since TransE came out. Although many translation-based approaches have achieved some progress in recent years, the performance was still unsatisfactory. This paper proposes a novel knowledge graph embedding method named TripleRE with two versions. The first version of TripleRE creatively divide the relationship vector into three parts. The second version takes advantage of the concept of residual and achieves better performance. In addition, attempts on using NodePiece to encode entities achieved promising results in reducing the parametric size, and solved the problems of scalability. Experiments show that our approach achieved state-of-the-art performance on the large-scale knowledge graph dataset, and competitive performance on other datasets.