Papers › PairRE: Knowledge Graph Embeddings via Paired Relation Vectors

PairRE: Knowledge Graph Embeddings via Paired Relation Vectors

7 Nov 2020ACL 2021 5arXiv:2011.03798archive 2025-07-28

Linlin Chao, Jianshan He, Taifeng Wang, Wei Chu

Distance based knowledge graph embedding methods show promising results on link prediction task, on which two topics have been widely studied: one is the ability to handle complex relations, such as N-to-1, 1-to-N and N-to-N, the other is to encode various relation patterns, such as symmetry/antisymmetry. However, the existing methods fail to solve these two problems at the same time, which leads to unsatisfactory results. To mitigate this problem, we propose PairRE, a model with paired vectors for each relation representation. The paired vectors enable an adaptive adjustment of the margin in loss function to fit for complex relations. Besides, PairRE is capable of encoding three important relation patterns, symmetry/antisymmetry, inverse and composition. Given simple constraints on relation representations, PairRE can encode subrelation further. Experiments on link prediction benchmarks demonstrate the proposed key capabilities of PairRE. Moreover, We set a new state-of-the-art on two knowledge graph datasets of the challenging Open Graph Benchmark.

PaperPDFConference PDFCode

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

Code

alipay/KnowledgeGraphEmbeddingsViaPairedRelationVectors_PairRE officialmentioned in papermentioned on GitHubpytorch 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 Graph EmbeddingsLink Prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-biokg PairRE Ext. data No #12 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg PairRE Number of params 187750000 #12 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg PairRE Test MRR 0.8164 ± 0.0005 #12 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg PairRE Validation MRR 0.8172 ± 0.0005 #12 of 16 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 PairRE (200dim) Ext. data No #21 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 PairRE (200dim) Number of params 500334800 #21 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 PairRE (200dim) Test MRR 0.5208 ± 0.0027 #21 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 PairRE (200dim) Validation MRR 0.5423 ± 0.0020 #21 of 30 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.

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