Corpus ID: 49310354

Canonical Tensor Decomposition for Knowledge Base Completion

@inproceedings{Lacroix2018CanonicalTD,
  title={Canonical Tensor Decomposition for Knowledge Base Completion},
  author={Timoth{\'e}e Lacroix and Nicolas Usunier and G. Obozinski},
  booktitle={ICML},
  year={2018}
}
The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) seems like a natural solution; however, current implementations of CP on standard Knowledge Base Completion benchmarks are lagging behind their competitors. In this work, we attempt to understand the limits of CP for knowledge base completion. First, we motivate and test a novel regularizer, based on tensor nuclear $p… Expand
127 Citations

Figures, Tables, and Topics from this paper

Adaptive Regularizing Tucker Decomposition for Knowledge Graph Completion
  • Highly Influenced
  • PDF
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
  • 2
  • Highly Influenced
  • PDF
Binarized Knowledge Graph Embeddings
  • 5
  • Highly Influenced
  • PDF
TuckER: Tensor Factorization for Knowledge Graph Completion
  • 128
  • PDF
Tensor Decompositions for temporal knowledge base completion
  • 13
  • PDF
Tucker decomposition-based Temporal Knowledge Graph Completion
  • PDF
Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
  • 11
  • PDF
TEMPORAL KNOWLEDGE BASE COMPLETION
  • Highly Influenced
Convolutional Complex Knowledge Graph Embeddings
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
On Tensor Completion via Nuclear Norm Minimization
  • 162
  • PDF
Complex Embeddings for Simple Link Prediction
  • 856
  • Highly Influential
  • PDF
Scalable and Sound Low-Rank Tensor Learning
  • 19
  • Highly Influential
  • PDF
A Three-Way Model for Collective Learning on Multi-Relational Data
  • 1,108
  • PDF
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
  • 1,013
  • Highly Influential
  • PDF
Multitask learning meets tensor factorization: task imputation via convex optimization
  • 44
  • PDF
Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases
  • 55
  • PDF
Learning Structured Embeddings of Knowledge Bases
  • 672
  • PDF
Convolutional 2D Knowledge Graph Embeddings
  • 616
  • PDF
...
1
2
3
4
...