{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T04:49:44Z","timestamp":1767156584856,"version":"3.40.5"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"type":"electronic","value":"9781643685373"}],"license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"abstract":"<jats:p>Knowledge Graphs (KGs) are relational knowledge bases that represent facts as a set of labelled nodes and the labelled relations between them. Their machine learning counterpart, Knowledge Graph Embeddings (KGEs), learn to predict new facts based on the data contained in a KG \u2013 the so-called link prediction task. To date, almost all forms of link prediction for KGs rely on some form of embedding model, and KGEs hold state-of-the-art status for link prediction. In this paper, we present TWIG-I (Topologically-Weighted Intelligence Generation for Inference), a novel link prediction system that can represent the features of a KG in latent space without using node or edge embeddings. TWIG-I shows mixed performance relative to state-of-the-art KGE models \u2013 at times exceeding or falling short of baseline performance. However, unlike KGEs, TWIG-I can be natively used for transfer learning across distinct KGs. We show that using transfer learning with TWIG-I can lead to increases in performance in some cases both over KGE baselines and over TWIG-I models trained without finetuning. While these results are still mixed, TWIG-I clearly demonstrates that structural features are sufficient to solve the link prediction task in the absence of embeddings. Finally, TWIG-I opens up cross-KG transfer learning as a new direction in link prediction research and application.<\/jats:p>","DOI":"10.3233\/ssw240010","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T07:45:58Z","timestamp":1726472758000},"source":"Crossref","is-referenced-by-count":1,"title":["TWIG-I: Embedding-Free Link Prediction and Cross-KG Transfer Learning Using a Small Neural Architecture"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0654-2938","authenticated-orcid":false,"given":"Jeffrey","family":"Sardina","sequence":"first","affiliation":[{"name":"Trinity College Dublin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1270-369X","authenticated-orcid":false,"given":"Alok","family":"Debnath","sequence":"additional","affiliation":[{"name":"Trinity College Dublin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6462-3248","authenticated-orcid":false,"given":"John D.","family":"Kelleher","sequence":"additional","affiliation":[{"name":"Trinity College Dublin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1090-3548","authenticated-orcid":false,"given":"Declan","family":"O\u2019Sullivan","sequence":"additional","affiliation":[{"name":"Trinity College Dublin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Studies on the Semantic Web","Knowledge Graphs in the Age of Language Models and Neuro-Symbolic AI"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SSW240010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T07:45:58Z","timestamp":1726472758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SSW240010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"ISBN":["9781643685373"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/ssw240010","relation":{},"ISSN":["1868-1158","2215-0870"],"issn-type":[{"type":"print","value":"1868-1158"},{"type":"electronic","value":"2215-0870"}],"subject":[],"published":{"date-parts":[[2024,9,11]]}}}