Corpus ID: 216562485

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

@article{Albooyeh2020OutofSampleRL,
  title={Out-of-Sample Representation Learning for Multi-Relational Graphs},
  author={Marjan Albooyeh and R. Goel and S. Kazemi},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.13230}
}
  • Marjan Albooyeh, R. Goel, S. Kazemi
  • Published 2020
  • Mathematics, 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
    Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES
    Inductive Representation Learning on Large Graphs
    • 2,003
    • Highly Influential
    • PDF
    Modeling Relational Data with Graph Convolutional Networks
    • 719
    • PDF
    Embedding Entities and Relations for Learning and Inference in Knowledge Bases
    • 758
    • PDF
    Representation Learning of Knowledge Graphs with Entity Descriptions
    • 279
    • Highly Influential
    • PDF
    Convolutional 2D Knowledge Graph Embeddings
    • 424
    • Highly Influential
    • PDF
    Graph Attention Networks
    • 1,736
    • PDF
    RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
    • 189
    • PDF
    Semi-Supervised Classification with Graph Convolutional Networks
    • 4,581
    • PDF
    Revisiting Semi-Supervised Learning with Graph Embeddings
    • 613
    • PDF
    Representation Learning on Graphs: Methods and Applications
    • 702
    • Highly Influential
    • PDF