HyperAI초신경

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

한국어

HyperAI초신경

Link Property Prediction On Ogbl Biokg

평가 지표

Number of params

Test MRR

Validation MRR

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Number of params	Test MRR	Validation MRR	Paper Title	Repository
ComplEx-N3-RP	187750000	0.8494	0.8497	Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
TransE	187648000	0.7452 ± 0.0004	0.7456 ± 0.0003	-	-
ComplEx	187648000	0.8095 ± 0.0007	0.8105 ± 0.0001	Complex Embeddings for Simple Link Prediction
GFA-NN	-	0.9011	0.9011	Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities	-
DistMult	187648000	0.8043 ± 0.0003	0.8055 ± 0.0003	Embedding Entities and Relations for Learning and Inference in Knowledge Bases
ComplEx^2	187648000	0.8583 ± 0.0005	0.8592 ± 0.0004	How to Turn Your Knowledge Graph Embeddings into Generative Models
ComplEx-RP (1000dim)	187750000	0.8492 ± 0.0002	0.8497 ± 0.0002	-	-
ComplEx^2	187648000	0.8583 ± 0.0005	0.8592 ± 0.0004	-	-
UniBi	181654170	0.8550 ± 0.0003	0.8553 ± 0.0001	Prior Bilinear Based Models for Knowledge Graph Completion
RelEns	849427106	0.9618 ± 0.0002	0.9627 ± 0.0004	Relation-aware Ensemble Learning for Knowledge Graph Embedding
AutoBLM-KGBench	192047104	0.8536 ± 0.0003	0.8548 ± 0.0002	Bilinear Scoring Function Search for Knowledge Graph Learning
AutoSF	93824000	0.8309 ± 0.0008	0.8317 ± 0.0007	AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
PairRE	187750000	0.8164 ± 0.0005	0.8172 ± 0.0005	PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
NBFNet	734,209	0.8317	0.8318	Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
TripleRE	469630002	0.8348 ± 0.0007	0.8360 ± 0.0006	-	-
RotatE	187597000	0.7989 ± 0.0004	0.7997 ± 0.0002	RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

0 of 16 row(s) selected.