Corpus ID: 218487333

Knowledge Base Completion: Baseline strikes back (Again)

@article{Jain2020KnowledgeBC,
  title={Knowledge Base Completion: Baseline strikes back (Again)},
  author={Prachi Jain and Sushant Rathi and Mausam and Soumen Chakrabarti},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.00804}
}
  • Prachi Jain, Sushant Rathi, +1 author Soumen Chakrabarti
  • Published 2020
  • Computer Science
  • ArXiv
  • Knowledge Base Completion has been a very active area recently, where multiplicative models have generally outperformed additive and other deep learning methods -- like GNN, CNN, path-based models. Several recent KBC papers propose architectural changes, new training methods, or even a new problem reformulation. They evaluate their methods on standard benchmark datasets - FB15k, FB15k-237, WN18, WN18RR, and Yago3-10. Recently, some papers discussed how 1-N scoring can speed up training and… CONTINUE READING
    4 Citations

    Tables from this paper

    CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
    • 4
    • PDF
    Explaining Neural Matrix Factorization with Gradient Rollback
    • PDF

    References

    SHOWING 1-10 OF 19 REFERENCES
    Knowledge Base Completion: Baselines Strike Back
    • 112
    • PDF
    You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings
    • 30
    • PDF
    Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision
    • 17
    • PDF
    Convolutional 2D Knowledge Graph Embeddings
    • 548
    • Highly Influential
    • PDF
    Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
    • 76
    • Highly Influential
    • PDF
    A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
    • 177
    • Highly Influential
    • PDF
    Modeling Relational Data with Graph Convolutional Networks
    • 937
    • Highly Influential
    • PDF
    Embedding Entities and Relations for Learning and Inference in Knowledge Bases
    • 908
    • PDF
    Canonical Tensor Decomposition for Knowledge Base Completion
    • 109
    • Highly Influential
    • PDF
    A Re-evaluation of Knowledge Graph Completion Methods
    • 24
    • Highly Influential
    • PDF