HyperAIHyperAI

Link Property Prediction On Ogbl Biokg

Métriques

Number of params
Test MRR
Validation MRR

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Number of params
Test MRR
Validation MRR
Paper TitleRepository
ComplEx-N3-RP1877500000.84940.8497Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations-
TransE1876480000.7452 ± 0.00040.7456 ± 0.0003--
ComplEx1876480000.8095 ± 0.00070.8105 ± 0.0001Complex Embeddings for Simple Link Prediction-
GFA-NN-0.90110.9011Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities-
DistMult1876480000.8043 ± 0.00030.8055 ± 0.0003Embedding Entities and Relations for Learning and Inference in Knowledge Bases-
ComplEx^21876480000.8583 ± 0.00050.8592 ± 0.0004How to Turn Your Knowledge Graph Embeddings into Generative Models-
ComplEx-RP (1000dim)1877500000.8492 ± 0.00020.8497 ± 0.0002--
ComplEx^21876480000.8583 ± 0.00050.8592 ± 0.0004--
UniBi1816541700.8550 ± 0.00030.8553 ± 0.0001Prior Bilinear Based Models for Knowledge Graph Completion-
RelEns8494271060.9618 ± 0.00020.9627 ± 0.0004Relation-aware Ensemble Learning for Knowledge Graph Embedding-
AutoBLM-KGBench1920471040.8536 ± 0.00030.8548 ± 0.0002Bilinear Scoring Function Search for Knowledge Graph Learning-
AutoSF938240000.8309 ± 0.00080.8317 ± 0.0007AutoSF: Searching Scoring Functions for Knowledge Graph Embedding-
PairRE1877500000.8164 ± 0.00050.8172 ± 0.0005PairRE: Knowledge Graph Embeddings via Paired Relation Vectors-
NBFNet734,2090.83170.8318Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction-
TripleRE4696300020.8348 ± 0.00070.8360 ± 0.0006--
RotatE1875970000.7989 ± 0.00040.7997 ± 0.0002RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space-
0 of 16 row(s) selected.
Link Property Prediction On Ogbl Biokg | SOTA | HyperAI