Corpus ID: 216562485

Out-of-Sample Representation Learning for Multi-Relational Graphs

  title={Out-of-Sample Representation Learning for Multi-Relational Graphs},
  author={Marjan Albooyeh and R. Goel and S. Kazemi},
  • Marjan Albooyeh, R. Goel, S. Kazemi
  • Published 2020
  • Computer Science
  • ArXiv
  • Many important problems can be formulated as reasoning in multi-relational graphs. Representation learning has proved extremely effective for transductive reasoning, in which one needs to make new predictions for already observed entities. This is true for both attributed graphs (where each entity has an initial feature vector) and non-attributed graphs(where the only initial information derives from known relations with other entities). For out-of-sample reasoning, where one needs to make… CONTINUE READING
    1 Citations

    Figures and Tables from this paper.

    Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
    • 1
    • PDF


    Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
    • 23
    • PDF
    Modeling Relational Data with Graph Convolutional Networks
    • 809
    • PDF
    Representation Learning of Knowledge Graphs with Entity Descriptions
    • 302
    • Highly Influential
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,270
    • Highly Influential
    • PDF
    RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
    • 229
    • PDF
    Embedding Entities and Relations for Learning and Inference in Knowledge Bases
    • 836
    • PDF
    Zero-Shot Embedding for Unseen Entities in Knowledge Graph
    • 2
    • PDF
    A Review of Relational Machine Learning for Knowledge Graphs
    • 811
    • PDF
    Convolutional 2D Knowledge Graph Embeddings
    • 497
    • Highly Influential
    • PDF
    Knowledge Graph Embedding via Dynamic Mapping Matrix
    • 544
    • PDF