Relation prediction on knowledge graphs (KGs) is a key research topic. Dominant embedding-based methods mainly focus on the transductive setting and lack the inductive ability to generalize to new entities for inference. Existing methods for inductive reasoning mostly mine the connections between entities, i.e., relational paths, without considering the nature of head and tail entities contained in the relational context. This paper proposes a novel method that captures both connections between entities and the intrinsic nature of entities, by simultaneously aggregating RElational Paths and cOntext with a unified hieRarchical Transformer framework, namely REPORT. REPORT relies solely on relation semantics and can naturally generalize to the fully-inductive setting, where KGs for training and inference have no common entities. In the experiments, REPORT performs consistently better than all baselines on almost all the eight version subsets of two fully-inductive datasets. Moreover. REPORT is interpretable by providing each element's contribution to the prediction results.
翻译:在知识图谱上进行关系预测是一个关键的研究课题。主流的基于嵌入的方法主要针对传导设置,并缺乏归纳能力,无法推广到新实体以进行推理。现有的归纳推理方法主要通过挖掘实体之间的连接(即关系路径),而不考虑包含在关系上下文中的头实体和尾实体的性质。本文提出了一种新的方法,通过统一的层次Transformer框架,同时聚合关系路径和上下文,捕捉实体之间的连接和实体本质的特性,即REPORT。REPORT仅依赖于关系语义,并能自然地推广到完全归纳的设置,其中训练和推理的知识图谱没有共同实体。在实验中,REPORT在两个完全归纳数据集的八个版本子集中几乎总是优于所有基线。此外,REPORT是可解释的,它提供了每个元素对预测结果的贡献。