Complex Query Answering On Nell 995
평가 지표
MRR 1p
MRR 2i
MRR 2p
MRR 2u
MRR 3i
MRR 3p
MRR ip
MRR pi
MRR up
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | MRR 1p | MRR 2i | MRR 2p | MRR 2u | MRR 3i | MRR 3p | MRR ip | MRR pi | MRR up |
|---|---|---|---|---|---|---|---|---|---|
| adapting-neural-link-predictors-for-complex | 0.604 | 0.434 | 0.229 | 0.200 | 0.526 | 0.167 | 0.264 | 0.321 | 0.170 |
| answering-complex-logical-queries-on | 0.607 | 0.425 | 0.241 | 0.204 | 0.506 | 0.216 | 0.265 | 0.313 | 0.179 |
| complex-query-answering-with-neural-link-1 | 0.604 | 0.436 | - | - | - | - | 0.256 | - | - |
| query2box-reasoning-over-knowledge-graphs-in-1 | 0.422 | 0.333 | 0.140 | 0.113 | 0.445 | 0.112 | 0.168 | 0.224 | 0.1103 |
| neural-symbolic-models-for-logical-queries-on | 0.533 | 0.424 | 0.189 | 0.159 | 0.525 | 0.149 | 0.189 | 0.308 | 0.126 |
| beta-embeddings-for-multi-hop-logical | 0.53 | 0.376 | 0.13 | 0.122 | 0.475 | 0.114 | 0.143 | 0.241 | 0.085 |