Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Link Prediction On Yago3 10

Metriken

Hits@1

Hits@10

Hits@3

MRR

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Hits@1	Hits@10	Hits@3	MRR	Paper Title	Repository
Rot-Pro	0.443	0.699	0.596	0.542	Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding
HAKE	0.462	0.694	0.596	0.545	Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
ComplEx	-	-	-	0.551	Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings
BoxE	0.494	0.699	-	0.567	BoxE: A Box Embedding Model for Knowledge Base Completion
RefE	0.503	0.712	0.621	0.577	Low-Dimensional Hyperbolic Knowledge Graph Embeddings
CP-DURA (large model)	0.506	0.709	-	0.579	Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion	-
DensE	0.465	0.678	0.585	0.541	DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy
ComplEx-DURA (large model)	0.511	0.713	-	0.584	Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion	-
DihEdral	0.381	0.643	0.523	0.472	Relation Embedding with Dihedral Group in Knowledge Graph	-
SAFRAN (white box, rule based)	0.492	0.693	-	0.564	SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models
NBFNet	0.480	0.708	0.612	0.563	Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
MEI	0.505	0.709	0.622	0.578	Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
A*Net	0.470	0.707	0.611	0.556	-	-
MEIM	0.514	0.716	0.625	0.585	MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction
ComplEx-N3 (reciprocal)	-	-	-	0.58	Canonical Tensor Decomposition for Knowledge Base Completion
InteractE	0.462	0.687	-	0.541	InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
ConvE	-	0.62	-	0.44	Convolutional 2D Knowledge Graph Embeddings
ComplEx-N3 (large model, reciprocal)	-	0.71	-	-	Canonical Tensor Decomposition for Knowledge Base Completion

0 of 18 row(s) selected.