HyperAI초신경

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

한국어

HyperAI초신경

Complex Query Answering On Fb15K

평가 지표

MRR 1p

MRR 2i

MRR 2p

MRR 2u

MRR 3i

MRR 3p

MRR ip

MRR pi

MRR up

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	MRR 1p	MRR 2i	MRR 2p	MRR 2u	MRR 3i	MRR 3p	MRR ip	MRR pi	MRR up	Paper Title	Repository
QTO	0.895	0.803	0.674	0.767	0.836	0.588	0.740	0.752	0.613	Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization
CQD-CO	-	-	-	-	-	-	-	-	-	Complex Query Answering with Neural Link Predictors
GNN-QE	0.885	0.797	0.693	0.741	0.835	0.587	0.704	0.699	0.610	Neural-Symbolic Models for Logical Queries on Knowledge Graphs
CQDA	0.892	0.761	0.645	0.684	0.794	0.579	0.706	0.701	0.579	Adapting Neural Link Predictors for Data-Efficient Complex Query Answering	-
GQE	0.546	0.397	0.153	0.221	0.514	0.108	0.191	0.276	0.116	Embedding Logical Queries on Knowledge Graphs
Q2B	0.68	0.551	0.21	0.351	0.665	0.142	0.261	0.394	0.167	Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
CQD	0.892	0.771	0.653	0.723	0.806	-	0.716	-	-	Complex Query Answering with Neural Link Predictors
CQD-Beam	-	-	-	-	-	-	-	-	-	Complex Query Answering with Neural Link Predictors
BetaE	0.651	0.558	0.257	0.401	0.665	0.247	0.281	0.439	0.252	Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

0 of 9 row(s) selected.