Papers › LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction

LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction

21 Apr 2020arXiv:2004.10037archive 2025-07-28

Yanhui Peng, Jing Zhang

The task of link prediction for knowledge graphs is to predict missing relationships between entities. Knowledge graph embedding, which aims to represent entities and relations of a knowledge graph as low dimensional vectors in a continuous vector space, has achieved promising predictive performance. If an embedding model can cover different types of connectivity patterns and mapping properties of relations as many as possible, it will potentially bring more benefits for link prediction tasks. In this paper, we propose a novel embedding model, namely LineaRE, which is capable of modeling four connectivity patterns (i.e., symmetry, antisymmetry, inversion, and composition) and four mapping properties (i.e., one-to-one, one-to-many, many-to-one, and many-to-many) of relations. Specifically, we regard knowledge graph embedding as a simple linear regression task, where a relation is modeled as a linear function of two low-dimensional vector-presented entities with two weight vectors and a bias vector. Since the vectors are defined in a real number space and the scoring function of the model is linear, our model is simple and scalable to large knowledge graphs. Experimental results on multiple widely used real-world datasets show that the proposed LineaRE model significantly outperforms existing state-of-the-art models for link prediction tasks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pengyanhui/LineaRE officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k LineaRE Hits@1 0.805 #2 of 10 Archive leaderboard report
Link Prediction FB15k LineaRE Hits@10 0.906 #2 of 10 Archive leaderboard report
Link Prediction FB15k LineaRE Hits@3 0.867 #2 of 10 Archive leaderboard report
Link Prediction FB15k LineaRE MR 36 #2 of 10 Archive leaderboard report
Link Prediction FB15k LineaRE MRR 0.843 #2 of 10 Archive leaderboard report
Link Prediction FB15k-237 LineaRE Hits@1 0.264 #24 of 75 Archive leaderboard report
Link Prediction FB15k-237 LineaRE Hits@10 0.545 #24 of 75 Archive leaderboard report
Link Prediction FB15k-237 LineaRE Hits@3 0.391 #24 of 75 Archive leaderboard report
Link Prediction FB15k-237 LineaRE MR 155 #24 of 75 Archive leaderboard report
Link Prediction FB15k-237 LineaRE MRR 0.357 #24 of 75 Archive leaderboard report
Link Prediction WN18 LineaRE Hits@1 0.947 #2 of 37 Archive leaderboard report
Link Prediction WN18 LineaRE Hits@10 0.961 #2 of 37 Archive leaderboard report
Link Prediction WN18 LineaRE Hits@3 0.955 #2 of 37 Archive leaderboard report
Link Prediction WN18 LineaRE MR 170 #2 of 37 Archive leaderboard report
Link Prediction WN18 LineaRE MRR 0.952 #2 of 37 Archive leaderboard report
Link Prediction WN18RR LineaRE Hits@1 0.453 #28 of 75 Archive leaderboard report
Link Prediction WN18RR LineaRE Hits@10 0.578 #28 of 75 Archive leaderboard report
Link Prediction WN18RR LineaRE Hits@3 0.509 #28 of 75 Archive leaderboard report
Link Prediction WN18RR LineaRE MR 1644 #28 of 75 Archive leaderboard report
Link Prediction WN18RR LineaRE MRR 0.495 #28 of 75 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Linear Regression

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections