论文标题
Interht：通过头部和尾部实体之间的相互作用嵌入知识图
InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities
论文作者
论文摘要
知识图嵌入（KGE）模型了解知识图中实体和关系的表示。基于距离的方法在链接预测任务上显示出有希望的性能，这通过两个实体表示之间的距离预测了结果。但是，这些方法中的大多数分别代表头部实体和尾部实体，这限制了模型容量。我们提出了两种名为InterHT和Interht+的新型基于距离的方法，这些方法允许头部和尾部实体更好地相互作用并获得更好的实体表示。实验结果表明，我们提出的方法在OGBL-Wikikg2数据集上获得了最佳结果。
Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs. Distance-based methods show promising performance on link prediction task, which predicts the result by the distance between two entity representations. However, most of these methods represent the head entity and tail entity separately, which limits the model capacity. We propose two novel distance-based methods named InterHT and InterHT+ that allow the head and tail entities to interact better and get better entity representation. Experimental results show that our proposed method achieves the best results on ogbl-wikikg2 dataset.
