PairRE: Knowledge Graph Embeddings via Paired Relation Vectors

ACL 2021  ·  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.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Property Prediction ogbl-biokg PairRE Test MRR 0.8164 ± 0.0005 # 12
Validation MRR 0.8172 ± 0.0005 # 12
Number of params 187750000 # 11
Ext. data No # 1
Link Property Prediction ogbl-wikikg2 PairRE (200dim) Validation MRR 0.5423 ± 0.0020 # 21
Test MRR 0.5208 ± 0.0027 # 21
Number of params 500334800 # 18
Ext. data No # 1

Methods


No methods listed for this paper. Add relevant methods here