TuckER: Tensor Factorization for Knowledge Graph Completion
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.
Code (5)
Tasks
Knowledge Graph CompletionKnowledge GraphsLink PredictionPredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TuckER: Tensor Factorization for Knowledge Graph Completion
Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is the task of inferring missing facts based on existing one…
Knowledge Graph CompletionKnowledge GraphsLink PredictionMulti-Task Learning+1Knowledge Graph Completion with Mixed Geometry Tensor Factorization
In this paper, we propose a new geometric approach for knowledge graph completion via low rank tensor approximation. We augment a pretrained and well-established Euclidean model based on a Tucker tensor decomposition wit…
Knowledge Graph CompletionKnowledge GraphsLink PredictionTensor Decomposition+1Projected Canonical Decomposition for Knowledge Base Completion
The leading approaches to tensor completion and link prediction are based on the canonical polyadic (CP) decomposition of tensors. While these approaches were originally motivated by low rank approximations, the best per…
Knowledge Base CompletionLink PredictionImplicit Regularization in Deep Tensor Factorization
Attempts of studying implicit regularization associated to gradient descent (GD) have identified matrix completion as a suitable test-bed. Late findings suggest that this phenomenon cannot be phrased as a minimization-no…
Matrix CompletionNePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
Knowledge graphs link entities through relations to provide a structured representation of real world facts. However, they are often incomplete, because they are based on only a small fraction of all plausible facts. The…
Knowledge Graph CompletionKnowledge GraphsLink PredictionPrediction