Deep Learning applied to Knowledge Graphs

Neural Networks

  1. Reasoning with neural tensor networks for knowledge base completion
  2. Probabilistic reasoning via deep learning: Neural association models
  3. Knowledge vault: A web-scale approach to probabilistic knowledge fusion

Convolutional Neural Networks

  1. Hypernetwork knowledge graph embeddings
  2. A novel embedding model for knowledge base completion based on convolutional neural network
  3. Convolutional 2d knowledge graph embeddings

Recurrent Neural Networks

  1. Learning to exploit long-term relational dependencies in knowledge graphs
  2. Compositional vector space models for knowledge base completion
  3. Incorporating vector space similarity in random walk inference over knowledge bases

Transformers

  1. KG-BERT: BERT for knowledge graph completion
  2. CoKE: Contextualized knowledge graph embedding

Graph Neural Networks

  1. Composition-based multi-relational graph convolutional networks
  2. Learning attention-based embeddings for relation prediction in knowledge graphs
  3. End-to-end structure-aware convolutional networks for knowledge base completion
  4. Modeling relational data with graph convolutional networks
  5. Semi-supervised classification with graph convolutional networks
Ryan

Ryan

Data Scientist

Leave a Reply