Link Prediction On Wn18Rr

评估指标

Hits@1

Hits@10

Hits@3

MRR

评测结果

各个模型在此基准测试上的表现结果

模型名称	Hits@1	Hits@10	Hits@3	MR	MRR	Paper Title	Repository
DensE	0.443	0.579	0.508	3052	0.491	DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy	-
SAttLE	0.454	0.558	0.508	-	0.491	Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction	-
NBFNet	0.497	0.666	0.573	636	0.551	Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction	-
RotH	0.449	0.586	0.514	-	.496	Low-Dimensional Hyperbolic Knowledge Graph Embeddings	-
HittER	0.462	0.584	0.516	-	0.503	HittER: Hierarchical Transformers for Knowledge Graph Embeddings	-
ComplEx-N3 (reciprocal)	-	0.57	-	-	0.48	Canonical Tensor Decomposition for Knowledge Base Completion	-
NePTuNe	0.455	0.557	0.507	-	0.491	NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion	-
RotatE + GreenKGC (Ours)	-	0.491	0.43	-	0.411	GreenKGC: A Lightweight Knowledge Graph Completion Method	-
DistMult (after variational EM)	-	-	-	-	0.455	Augmenting and Tuning Knowledge Graph Embeddings	-
LERP	0.593	0.682	0.634	-	0.622	Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning	-
ComplEx NSCaching	-	0.5089	-	5365	0.4463	NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding	-
ConE	0.453	0.579	0.515	-	0.496	Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones	-
CapsE	-	0.56	-	719.0	0.415	A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization	-
MoCoSA	0.624	0.82	0.737	-	0.696	MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented Pre-trained Language Models	-
DRUM (T=3)	0.425	0.586	0.513	-	0.486	DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs	-
PALT	-	0.693	-	61	-	PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion	-
HAKE	0.452	0.582	0.516	-	0.497	Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction	-
LineaRE	0.453	0.578	0.509	1644	0.495	LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction	-
KGRefiner	-	0.57	-	683	0.448	KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods	-
DisMult	0.39	-	-	-	0.43	Embedding Entities and Relations for Learning and Inference in Knowledge Bases	-

0 of 74 row(s) selected.