Corpus ID: 38485677

Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

  title={Knowledge Graph Completion with Adaptive Sparse Transfer Matrix},
  author={Guoliang Ji and Kang Liu and Shizhu He and Jun Zhao},
  • Guoliang Ji, Kang Liu, +1 author Jun Zhao
  • Published in AAAI 2016
  • Computer Science
  • We model knowledge graphs for their completion by encoding each entity and relation into a numerical space. All previous work including Trans(E, H, R, and D) ignore the heterogeneity (some relations link many entity pairs and others do not) and the imbalance (the number of head entities and that of tail entities in a relation could be different) of knowledge graphs. In this paper, we propose a novel approach TranSparse to deal with the two issues. In TranSparse, transfer matrices are replaced… CONTINUE READING
    205 Citations

    Figures, Tables, and Topics from this paper

    A Re-Ranking Framework for Knowledge Graph Completion
    • PDF
    Relation path embedding in knowledge graphs
    • 9
    • Highly Influenced
    • PDF
    A Survey on Knowledge Graph Embedding: Approaches, Applications and Benchmarks
    • 5
    • PDF
    A Novel Asymmetric Embedding Model for Knowledge Graph Completion
    Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
    • 4
    • PDF


    Knowledge Graph Embedding via Dynamic Mapping Matrix
    • 592
    • PDF
    Learning Entity and Relation Embeddings for Knowledge Graph Completion
    • 1,321
    • Highly Influential
    • PDF
    Learning to Represent Knowledge Graphs with Gaussian Embedding
    • 190
    • PDF
    A latent factor model for highly multi-relational data
    • 309
    • PDF
    Knowledge Graph Embedding by Translating on Hyperplanes
    • 1,281
    • Highly Influential
    Semantically Smooth Knowledge Graph Embedding
    • 94
    • PDF
    Translating Embeddings for Modeling Multi-relational Data
    • 2,565
    • Highly Influential
    • PDF
    Reasoning With Neural Tensor Networks for Knowledge Base Completion
    • 1,286
    • Highly Influential
    • PDF
    Learning Structured Embeddings of Knowledge Bases
    • 657
    • PDF
    A Review of Relational Machine Learning for Knowledge Graphs
    • 850
    • PDF