A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings

TL;DR

This survey reviews the relationship between knowledge graph structures and embedding models, highlighting how structure influences model performance and biases, and aims to guide future research in this area.

Contribution

It is the first comprehensive survey exploring how knowledge graph structure impacts embedding models and link prediction performance.

Findings

KG structure significantly affects embedding model outcomes.

Biases in KGs can influence link prediction results.

Understanding structure-model interactions can improve KGEMs.

Abstract

Knowledge Graphs (KGs) and their machine learning counterpart, Knowledge Graph Embedding Models (KGEMs), have seen ever-increasing use in a wide variety of academic and applied settings. In particular, KGEMs are typically applied to KGs to solve the link prediction task; i.e. to predict new facts in the domain of a KG based on existing, observed facts. While this approach has been shown substantial power in many end-use cases, it remains incompletely characterised in terms of how KGEMs react differently to KG structure. This is of particular concern in light of recent studies showing that KG structure can be a significant source of bias as well as partially determinant of overall KGEM performance. This paper seeks to address this gap in the state-of-the-art. This paper provides, to the authors' knowledge, the first comprehensive survey exploring established relationships of Knowledge Graph Embedding Models and Graph structure in the literature. It is the hope of the authors that this work will inspire further studies in this area, and contribute to a more holistic understanding of KGs, KGEMs, and the link prediction task.