Corpus ID: 220265751

Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion

@article{Tran2020MultiPartitionEI,
  title={Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion},
  author={Hung Nghiep Tran and Atsuhiro Takasu},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16365}
}
  • Hung Nghiep Tran, Atsuhiro Takasu
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between these whole embeddings, potentially making the model excessively expensive or requiring… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Convolutional 2D Knowledge Graph Embeddings

    VIEW 14 EXCERPTS
    HIGHLY INFLUENTIAL

    Decompositions of a Higher-Order Tensor in Block Terms - Part II: Definitions and Uniqueness

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Holographic Embeddings of Knowledge Graphs

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    SimplE Embedding for Link Prediction in Knowledge Graphs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Some mathematical notes on three-mode factor analysis

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    TorusE: Knowledge Graph Embedding on a Lie Group

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL