Knowledge graph embedding models (KGEMs) developed for link prediction learn
vector representations for graph entities, known as embeddings. A common tacit
assumption is the KGE entity similarity assumption, which states that these
KGEMs retain the graph's structure within their embedding space, i.e., position
similar entities close to one another. This desirable property make KGEMs
widely used in downstream tasks such as recommender systems or drug
repurposing. Yet, the alignment of graph similarity with embedding space
similarity has rarely been formally evaluated. Typically, KGEMs are assessed
based on their sole link prediction capabilities, using ranked-based metrics
such as Hits@K or Mean Rank. This paper challenges the prevailing assumption
that entity similarity in the graph is inherently mirrored in the embedding
space. Therefore, we conduct extensive experiments to measure the capability of
KGEMs to cluster similar entities together, and investigate the nature of the
underlying factors. Moreover, we study if different KGEMs expose a different
notion of similarity. Datasets, pre-trained embeddings and code are available
at: this https URL

知识图谱嵌入模型（KGEM）被用于链接预测，学习图谱实体的向量表示，这些模型中的 KGEM 实体相似性假设保持了图谱结构在嵌入空间中的位置相似性，而本文对实体在图谱中与嵌入空间中的相似性进行了正式评估，并研究不同 KGEM 模型的相似性概念。