Skip to content

melissakou/knowledge-graph-embedding

Repository files navigation

Knowledge Graph Embedding

Documentation Status
A TensorFlow-based implementation of knowledge graph embedding models.
Document available here: https://knowledge-graph-embedding.readthedocs.io/en/latest/index.html

Todos

  • finish docs
  • unit test
  • model saving
  • early stopping with ranking metric (for now using validation loss)
  • reproducible paper experiment

Models

Including following knowledge graph embedding model:

Translating Based

  • Unstructured Model (UM)
  • Structured Embedding (SE)
  • TransE
  • TransH
  • TransR
  • TransD
  • RotatE

Semantic Based

  • RESCAL
  • DistMult

Loss

  • Pairwise Hinge Loss
  • Pairwise Logistic Loss
  • Binary Cross Entropy Loss
  • Self Adversarial Negative Sampling Loss
  • Square Error Loss

Score

  • Dot
  • Lp-Distance
  • Squared Lp-Distance

Constraint

  • Lp-Regularization
  • Clip Constraint
  • Nomalized Embedding
  • Soft Constraint

Negative Sampling Strategy

  • Uniform Strategy
  • Typed Strategy
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy