HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Link Prediction On Wikidata5M

평가 지표

Hits@1

Hits@10

Hits@3

MRR

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Hits@1	Hits@10	Hits@3	MRR	Paper Title	Repository
DistMult	0.208	0.334	0.278	0.253	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
SimplE	0.252	0.377	0.317	0.296	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
KGT5-context + Description	0.406	0.46	0.44	0.426	Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
MoCoKGC	0.435	0.591	0.517	0.490	MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion	-
KGT5 ComplEx Ensemble	0.282	0.426	0.362	0.336	Sequence-to-Sequence Knowledge Graph Completion and Question Answering
ComplEx	0.228	0.373	0.310	0.281	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
KGT5 + Description	0.357	0.422	0.397	0.381	Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
TransE	0.17	0.392	0.311	0.253	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
KGT5-context	0.35	0.427	0.396	0.378	Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
KGT5	0.267	0.365	0.318	0.300	Sequence-to-Sequence Knowledge Graph Completion and Question Answering
ComplEx	0.255	0.398	-	0.308	Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques
RotatE	0.234	0.39	0.322	0.29	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
KEPLER-Wiki-rel	0.173	0.277	0.224	0.210	KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
SimKGC + Description	0.313	0.441	0.376	0.358	SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models

0 of 14 row(s) selected.