TuckER: Tensor Factorization for Knowledge Graph Completion

Code

• github.com/ibalazevic/TuckER
  OfficialIn paperpytorch★ 0
• github.com/luffycodes/neptune
  pytorch★ 16
• github.com/adaruna3/explainable-kge
  pytorch★ 9
• github.com/allenai/kb
  pytorch★ 0
• github.com/Sujit-O/pykg2vec
  tf★ 0

Abstract

Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is a task of inferring missing facts based on existing ones. We propose TuckER, a relatively straightforward but powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples. TuckER outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models. We show that TuckER is a fully expressive model, derive sufficient bounds on its embedding dimensionalities and demonstrate that several previously introduced linear models can be viewed as special cases of TuckER.

Tasks

Benchmark Results

Reproductions