Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities' contextual information. Specifically, we design two inference mechanisms: i) N2T: independently use each neighbor of an entity to infer its type; ii) Agg2T: aggregate the neighbors of an entity to infer its type. Those mechanisms will produce multiple inference results, and an exponentially weighted pooling method is used to generate the final inference result. Furthermore, we propose a novel loss function to alleviate the false-negative problem during training. Experiments on two real-world KGs demonstrate the effectiveness of our method. The source code and data of this paper can be obtained from https://github.com/CCIIPLab/CET.

中文翻译：

---

知识图中的上下文感知实体类型

知识图实体分类旨在推断知识图中实体的缺失类型，这是一个重要但未充分探索的问题。本文通过利用实体的上下文信息为该任务提出了一种新方法。具体来说，我们设计了两种推理机制： i) N2T：独立使用实体的每个邻居来推断其类型；ii) Agg2T：聚合实体的邻居以推断其类型。这些机制将产生多个推理结果，并使用指数加权池化方法生成最终推理结果。此外，我们提出了一种新的损失函数来减轻训练过程中的假阴性问题。在两个真实世界的 KG 上的实验证明了我们方法的有效性。本文源代码和数据可从https://github.com/CCIIPLab/CET获取。