论文标题
配对：通过配对关系向量的知识图嵌入
PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
论文作者
论文摘要
基于距离的知识图嵌入方法在链接预测任务上显示了有希望的结果，在链接预测任务上已经广泛研究了两个主题：一个是处理复杂关系的能力，例如n-to-1，1-1-to-n和n-to-n，例如，另一种是编码各种关系模式，例如对称性/反对称模式。但是，现有方法无法同时解决这两个问题，从而导致结果不令人满意。为了减轻此问题，我们提出了配对，这是一个具有配对向量的模型，用于每个关系表示。配对矢量可以自适应调整损耗函数的边缘，以适合复杂关系。此外，Pairre能够编码三种重要的关系模式，对称性/反对称性，逆和组成。给定对关系表示的简单限制，成对可以进一步编码子关系。链接预测基准的实验证明了成对的提议的关键功能。此外，我们在具有挑战性的开放图基准测试的两个知识图数据集上设置了一个新的最先进。
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.
