Link Prediction On Fb15K 237
Metriken
Hits@10
MR
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Hits@10 | MR |
|---|---|---|
| joint-language-semantic-and-structure | 0.533 | 108 |
| rotate-knowledge-graph-embedding-by | 0.524 | 178 |
| palt-parameter-lite-transfer-of-language | 0.444 | 144 |
| duality-induced-regularizer-for-tensor | 0.560 | - |
| multi-partition-embedding-interaction-with | 0.552 | - |
| mde-multi-distance-embeddings-for-link | 0.531 | 203 |
| composition-based-multi-relational-graph | 0.535 | 197 |
| mocosa-momentum-contrast-for-knowledge-graph | 0.578 | - |
| logicenn-a-neural-based-knowledge-graphs | 0.473 | 424 |
| kgrefiner-knowledge-graph-refinement-for | 0.489 | 203 |
| hypernetwork-knowledge-graph-embeddings | 0.520 | - |
| neural-bellman-ford-networks-a-general-graph | 0.599 | 114 |
| simkgc-simple-contrastive-knowledge-graph | 0.511 | - |
| self-distillation-with-meta-learning-for-1 | 0.571 | - |
| mlmlm-link-prediction-with-mean-likelihood | 0.4026 | 411 |
| a-retrieve-and-read-framework-for-knowledge | - | - |
| low-dimensional-hyperbolic-knowledge-graph-1 | 0.541 | - |
| quaternion-knowledge-graph-embedding | 0.550 | 87 |
| kbgan-adversarial-learning-for-knowledge | 0.458 | - |
| end-to-end-structure-aware-convolutional | 0.54 | - |
| from-discrimination-to-generation-knowledge | 0.439 | - |
| hitter-hierarchical-transformers-for | - | - |
| a-re-evaluation-of-knowledge-graph-completion | .331 | 270 |
| lp-bert-multi-task-pre-training-knowledge | 0.490 | 154 |
| nscaching-simple-and-efficient-negative | 0.4805 | 221 |
| kglm-integrating-knowledge-graph-structure-in | 0.468 | 125.9 |
| a-retrieve-and-read-framework-for-knowledge | 0.539 | - |
| greenkgc-a-lightweight-knowledge-graph | 0.507 | - |
| tucker-tensor-factorization-for-knowledge | 0.544 | - |
| orthogonal-relation-transforms-with-graph | 0.550 | 154 |
| a-re-evaluation-of-knowledge-graph-completion | .057 | 446 |
| embedding-knowledge-graphs-attentive-to | 0.522 | 186 |
| translating-embeddings-for-modeling-multi | .4709 | - |
| learning-hierarchy-aware-knowledge-graph | - | - |
| greenkgc-a-lightweight-knowledge-graph | 0.493 | - |
| modeling-heterogeneous-hierarchies-with | 0.54 | - |
| knowledge-graph-embedding-with-linear | 0.545 | 155 |
| reasoning-through-memorization-nearest | 0.550 | 185 |
| using-pairwise-occurrence-information-to | 0.479 | - |
| augmenting-and-tuning-knowledge-graph | 0.548 | - |
| drum-end-to-end-differentiable-rule-mining-on | 0.516 | - |
| kermit-knowledge-graph-completion-of-enhanced | 0.547 | - |
| relation-prediction-as-an-auxiliary-training | 0.535 | - |
| boxe-a-box-embedding-model-for-knowledge-base | 0.538 | - |
| mocokgc-momentum-contrast-entity-encoding-for | 0.580 | - |
| adaptive-convolution-for-multi-relational | 0.528 | - |
| autokge-searching-scoring-functions-for | 0.555 | - |
| relation-prediction-as-an-auxiliary-training | 0.568 | 163 |
| relation-prediction-as-an-auxiliary-training | 0.55 | - |
| interacte-improving-convolution-based | 0.535 | 172 |
| semantic-triple-encoder-for-fast-open-set | 0.562 | 117 |
| meim-multi-partition-embedding-interaction | 0.557 | - |
| graphvite-a-high-performance-cpu-gpu-hybrid | 0.511 | 176 |
| a-re-evaluation-of-knowledge-graph-completion | .421 | 309 |
| decompressing-knowledge-graph-representations | 0.536 | - |
| kg-bert-bert-for-knowledge-graph-completion | 0.42 | 153 |
| embedding-entities-and-relations-for-learning | 0.419 | - |
| rotate-knowledge-graph-embedding-by | 0.533 | 177 |
| multi-relational-poincare-graph-embeddings | 0.521 | - |
| dense-an-enhanced-non-abelian-group | 0.535 | 169 |
| unified-interpretation-of-softmax-cross | 0.548 | - |
| knowledge-graph-embedding-via-dynamic-mapping | 0.4605 | - |
| how-does-knowledge-graph-embedding | 0.549 | 157 |
| self-attention-presents-low-dimensional | 0.545 | - |
| quatde-dynamic-quaternion-embedding-for | 0.563 | 90 |
| unified-interpretation-of-softmax-cross | 0.55 | - |
| relphormer-relational-graph-transformer-for | 0.481 | - |
| rot-pro-modeling-transitivity-by-projection | 0.540 | - |
| convolutional-2d-knowledge-graph-embeddings | 0.014 | 7030 |
| convolutional-2d-knowledge-graph-embeddings | 0.501 | - |
| r-gcn-the-r-could-stand-for-random | 0.412 | - |
| safran-an-interpretable-rule-based-link | 0.537 | - |
| complex-embeddings-for-simple-link-prediction | 0.428 | - |
| neptune-neural-powered-tucker-network-for | 0.547 | - |