PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
This work addresses limitations in knowledge graph embedding methods for researchers and practitioners in AI, offering an incremental improvement over existing approaches.
The authors tackled the problem of knowledge graph embedding for link prediction by proposing PairRE, a model using paired relation vectors to handle complex relations and encode multiple relation patterns simultaneously, achieving new state-of-the-art results on two Open Graph Benchmark datasets.
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.