Corpus ID: 214774812

Improving the Utility of Knowledge Graph Embeddings with Calibration

@article{Safavi2020ImprovingTU,
  title={Improving the Utility of Knowledge Graph Embeddings with Calibration},
  author={Tara Safavi and Danai Koutra and E. Meij},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.01168}
}
This paper addresses machine learning models that embed knowledge graph entities and relationships toward the goal of predicting unseen triples, which is an important task because most knowledge graphs are by nature incomplete. We posit that while offline link prediction accuracy using embeddings has been steadily improving on benchmark datasets, such embedding models have limited practical utility in real-world knowledge graph completion tasks because it is not clear when their predictions… Expand

References

SHOWING 1-10 OF 37 REFERENCES
Probability Calibration for Knowledge Graph Embedding Models
Revisiting Evaluation of Knowledge Base Completion Models
CoDEx: A Comprehensive Knowledge Graph Completion Benchmark
On Evaluating Embedding Models for Knowledge Base Completion
Convolutional 2D Knowledge Graph Embeddings
Representation Learning of Knowledge Graphs with Hierarchical Types
KGAT: Knowledge Graph Attention Network for Recommendation
Complex Embeddings for Simple Link Prediction
Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications
...
1
2
3
4
...