Abstract
Hyper-relational knowledge graphs (KGs) contain additional key-value pairs, providing more information about the relations. In many scenarios, the same relation can have distinct key-value pairs, making the original triple fact more recognizable and specific. Prior studies on hyper-relational KGs have established a solid standard method for hyper-relational graph encoding. In this work, we propose a message-passing-based graph encoder with global relation structure awareness ability, which we call ReSaE. Compared to the prior state-of-the-art approach, ReSaE emphasizes the interaction of relations during message passing process and optimizes the readout structure for link prediction tasks. Overall, ReSaE gives a encoding solution for hyper-relational KGs and ensures stronger performance on downstream link prediction tasks. Our experiments demonstrate that ReSaE achieves state-of-the-art performance on multiple link prediction benchmarks. Furthermore, we also analyze the influence of different model structures on model performance.
Abstract (translated)
超关系知识图（KGs）包含附加的关键值对，提供了关于关系更多信息。在许多场景中，相同的关系可能具有不同的关键值对，使得原始三元组更易识别和具体。关于超关系KGs的前期研究已经建立了一个可靠的超关系图编码方法。在这项工作中，我们提出了一个基于消息传递的图编码器，我们称之为ReSaE。与最先进的现有方法相比，ReSaE突出了关系在消息传递过程中互动，并优化了链路预测任务的输出结构。总体而言，ReSaE为超关系KGs提供了编码解决方案，并在下游链路预测任务中实现了更强的性能。我们的实验结果表明，ReSaE在多个链路预测基准测试中实现了最先进的性能。此外，我们还分析了不同模型结构对模型性能的影响。
URL
https://arxiv.org/abs/2402.15140
