Link Prediction On Wordnet

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Hyperbolic Entailment Cones	94.4	Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Poincare Embeddings (dim=100)	77.4	Poincaré Embeddings for Learning Hierarchical Representations
Poincare Embeddings (dim=50)	77.0	Poincaré Embeddings for Learning Hierarchical Representations
Poincare Embeddings (dim=20)	74.3	Poincaré Embeddings for Learning Hierarchical Representations
Poincare Embeddings (dim=10)	68.3	Poincaré Embeddings for Learning Hierarchical Representations
Hyper-SAGNN-W	-	Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
Hyper-SAGNN-E	-	Hyper-SAGNN: a self-attention based graph neural network for hypergraphs

0 of 7 row(s) selected.