Scoring Functions

There are generally two types of scoring function: Translational distance-based and Semantic matching-based. Here’s a list of papers to read!

Translational distance-based

  1. Learning entity and relation embeddings for knowledge graph completion
  2. Knowledge graph embedding by translating on hyperplanes
  3. Translating embeddings for modeling multi-relational data
  4. From one point to a manifold: Orbit models for knowledge graph embedding
  5. Learning to represent knowledge graphs with gaussian embedding
  6. TransMS: knowledge graph embedding for complex relations by multidirectional semantics
  7. Translating embeddings for knowledge graph completion with relation attention mechanism
  8. An interpretable knowledge transfer model for knowledge base completion
  9. Knowledge graph embedding by flexible translation
  10. TransA: An adaptive approach for knowledge graph embedding
  11. Knowledge graph embedding via dynamic mapping matrix
  12. Learning structured embeddings of knowledge bases

Semantic matching-based

  1. Analogical inference for multi-relational embeddings
  2. Holographic embeddings of knowledge graphs
  3. Relation embedding with dihedral group in knowledge graph
  4. TorusE: Knowledge graph embedding on a liegroup
  5. LowFER: Low-rank bilinear pooling for link prediction
  6. TuckER: Tensor factorization for knowledge graph completion
  7. Interaction embeddings for prediction and explanation in knowledge graphs
  8. SimplE embedding for link prediction in knowledge graphs
  9. Expanding holographic embeddings for knowledge completion
  10. Embedding entities and relations for learning and inference in knowledge bases
  11. A semantic matching energy function for learning with multi-relational data
  12. A latent factor model for highly multi-relational data
  13. Learning structured embeddings of knowledge bases
  14. A three-way model for collective learning on multi-relational data
Ryan

Ryan

Data Scientist

Leave a Reply