Encoding Models & Auxiliary Information

Linear/Bilinear Encoding Models

  1. Analogical inference for multi-relational embeddings
  2. Translating embeddings for modeling multi-relational data
  3. Complex embeddings for simple link prediction
  4. On multi-relational link prediction with bilinear models
  5. SimplE embedding for link prediction in knowledge graphs
  6. Embedding entities and relations for learning and inference in knowledge bases
  7. A semantic matching energy function for learning with multi-relational data
  8. Learning structured embeddings of knowledge bases

Factorisation Encoding Models

  1. LowFER: Low-rank bilinear pooling for link prediction
  2. TuckER: Tensor factorization for knowledge graph completion
  3. A latent factor model for highly multi-relational data
  4. Factorizing YAGO: scalable machine learning for linked data
  5. A three-way model for collective learning on multi-relational data

Embedding with Auxiliary Information (TYPE)

  1. Knowledge graph embedding with hierarchical relation structure
  2. Knowledge representation learning with entities, attributes and relations
  3. Representation learning of knowledge graphs with hierarchical types
  4. Semantically smooth knowledge graph embedding

Embedding with Auxiliary Information (VISUAL)

  1. Image-embodied knowledge representation learning

Embedding with Auxiliary Information (TEXT)

  1. Relation extraction using supervision from topic knowledge of relation labels
  2. Cooperative denoising for distantly supervised relation extraction
  3. SP: semantic space projection for knowledge graph embedding with text descriptions
  4. Representation learning of knowledge graphs with entity descriptions
  5. Knowledge graph and text jointly embedding
Ryan

Ryan

Data Scientist

Leave a Reply