2025/12/01 by Jeffrey Sardina, John D. Kelleher, Declan O’Sullivan · 1 voice
Computer Science · Biochemistry, Genetics and Molecular Biology · #Advanced Graph Neural Networks #Graph Theory and Algorithms #Bioinformatics and Genomic Networks
paper · doi:10.1142/s1793351x25450060
openalex publication_date 2025/12/01 · openalex created_date 2025/12/15 · openalex updated_date 2026/08/01
Knowledge Graphs (KGs) have seen ever-increasing use in a breadth of academic and applied settings. In tandem with the increasing use of KGs, there has been an increased interest in the Link Prediction (LP) task, which aims to predict new information about the domain of a KG based on the data in the KG. While Knowledge Graph Embedding Models (KGEMs) have predominantly been used to solve the LP task in the state-of-the-art, both KGEMs and the LP task remain incompletely characterized in terms of how they relate to the structure of the KG being learned. This is of particular concern in light of recent studies showing that KG structure can be both a significant source of bias in LP learning and at least partially determinant of LP performance. This paper seeks to address this gap in the state-of-the-art by providing a survey of the established relationships between LP, KGEMs, and KG structure in the literature. This work then proposes the Structural Alignment Hypothesis as a unifying perspective for modeling the data-task relationship between KGs and LP. It is the hope of the authors that this work will contribute to a more holistic understanding of KGs, KGEMs, and the LP task.