Knowledge graphs (KGs) have become effective knowledge resources in diverse applications, and knowledge graph embedding (KGE) methods have attracted increasing attention in recent years. However, it's still challenging for conventional KGE methods to handle unseen entities or relations during the model test. Much effort has been made in various fields of KGs to address this problem. In this paper, we use a set of general terminologies to unify these methods and refer to them as Knowledge Extrapolation. We comprehensively summarize these methods classified by our proposed taxonomy and describe their correlations. Next, we introduce the benchmarks and provide comparisons of these methods from aspects that are not reflected by the taxonomy. Finally, we suggest some potential directions for future research.

翻译：知识图谱（KG）已成为多种应用中的有效知识资源，近年来知识图谱嵌入（KGE）方法日益受到关注。然而，传统KGE方法在模型测试阶段处理未见实体或关系时仍面临挑战。针对这一问题，各知识图谱研究领域已投入大量努力。本文采用一套通用术语统一这些方法，并将其统称为知识外推。我们基于提出的分类体系对这类方法进行了全面归纳，描述了其内在关联。随后，我们介绍了基准评估，并从分类体系未直接反映的维度对这些方法进行了比较分析。最后，我们提出了若干未来研究的潜在方向。