Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/HHolE

HHolE

Reported on 19 benchmarks across 5 tasks · 1 paper · 9 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Graphs15 results

Link Predictionon FB15k
Hits@10· 2018-11-02
0.901
best: 0.914 (AutoKGE)
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link Predictionon FB15k
Hits@3· 2018-11-02
0.848
best: 0.859 (QuatE)
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link Predictionon FB15k
MRR· 2018-11-02
0.796
best: 0.861 (AutoKGE)
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononFB15k
Hits@1· 2018-11-02
0.727
best: 0.805 (LineaRE)
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononFB15k
Hits@3· 2018-11-02
0.848
best: 0.867 (LineaRE)
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link Predictionon FB15k
Hits@1· 2018-11-02
0.727
best: 0.8 (QuatE)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link Predictionon FB15k
MR· 2018-11-02
21
best: 2501 (Inverse Model)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononFB15k
Hits@10· 2018-11-02
0.901
best: 0.91 (ComplEx-N3 (reciprocal))
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononFB15k
MR· 2018-11-02
21
best: 82 (ComplEx NSCaching)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononFB15k
MRR· 2018-11-02
0.796
best: 0.86 (ComplEx-N3 (reciprocal))
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononWN18
Hits@1· 2018-11-02
0.931
best: 0.953 (Inverse Model)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononWN18
Hits@10· 2018-11-02
0.951
best: 0.964 (Inverse Model)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononWN18
Hits@3· 2018-11-02
0.945
best: 0.964 (Inverse Model)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononWN18
MR· 2018-11-02
183
best: 1072 (ComplEx NSCaching)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Link PredictiononWN18
MRR· 2018-11-02
0.939
best: 0.963 (Inverse Model)
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062

Knowledge Base2 results

Knowledge Graphson FB15k
MRR· 2018-11-02
0.796
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062
Knowledge Graph Completionon FB15k
MRR· 2018-11-02
0.796
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062

Methodology1 result

Large Language Modelon FB15k
MRR· 2018-11-02
0.796
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062

Natural Language Processing1 result

Inductive knowledge graph completionon FB15k
MRR· 2018-11-02
0.796
SOTA
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations arXiv:1811.01062