{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/structural-alignment-in-link-prediction","title":"Structural Alignment in Link Prediction","arxiv_id":"2505.04939","date":"2025-05-08","proceeding":null,"authors":["Jeffrey Seathrún Sardina"],"abstract":"While Knowledge Graphs (KGs) have become increasingly popular across various scientific disciplines for their ability to model and interlink huge quantities of data, essentially all real-world KGs are known to be incomplete. As such, with the growth of KG use has been a concurrent development of machine learning tools designed to predict missing information in KGs, which is referred to as the Link Prediction Task. The majority of state-of-the-art link predictors to date have followed an embedding-based paradigm. In this paradigm, it is assumed that the information content of a KG is best represented by the (individual) vector representations of its nodes and edges, and that therefore node and edge embeddings are particularly well-suited to performing link prediction. This thesis proposes an alternative perspective on the field's approach to link prediction and KG data modelling. Specifically, this work re-analyses KGs and state-of-the-art link predictors from a graph-structure-first perspective that models the information content of a KG in terms of whole triples, rather than individual nodes and edges. Following a literature review and two core sets of experiments, this thesis concludes that a structure-first perspective on KGs and link prediction is both viable and useful for understanding KG learning and for enabling cross-KG transfer learning for the link prediction task. This observation is used to create and propose the Structural Alignment Hypothesis, which postulates that link prediction can be understood and modelled as a structural task. All code and data used for this thesis are open-sourced. This thesis was written bilingually, with the main document in English and an informal extended summary in Irish. An Irish-language translation dictionary of machine learning terms (the Focl\\'oir Tr\\'achtais) created for this work is open-sourced as well.","url_abs":"https://arxiv.org/abs/2505.04939v1","url_pdf":"https://arxiv.org/pdf/2505.04939v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"structural-alignment-in-link-prediction","repo_url":"https://github.com/Jeffrey-Sardina/TWIG-I","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"structural-alignment-in-link-prediction","repo_url":"https://github.com/Jeffrey-Sardina/TWIG-TWM-dev","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}