@inproceedings{2f9d600c61c4491ead064c37c9df9a79,
title = "Designing Hierarchies for Optimal Hyperbolic Embedding",
abstract = "Hyperbolic geometry has shown to be highly effective for embedding hierarchical data structures. As such, machine learning in hyperbolic space is rapidly gaining traction across a wide range of disciplines, from recommender systems and graph networks to biological systems and computer vision. The performance of hyperbolic learning commonly depends on the hierarchical information used as input or supervision. Given that knowledge graphs and ontologies are common sources of such hierarchies, this paper aims to guide ontology designers in designing hierarchies for use in these learning algorithms. Using widely employed measures of embedding quality with extensive experiments, we find that hierarchies are best suited for hyperbolic embeddings when they are wide, and single inheritance, independent of the hierarchy size and imbalance.",
keywords = "Hyperbolic Learning, Machine Learning, Ontology Design",
author = "Melika Ayoughi and {van Spengler}, Max and Pascal Mettes and Paul Groth",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 22nd European Semantic Web Conference, ESWC 2025 ; Conference date: 01-06-2025 Through 05-06-2025",
year = "2025",
doi = "10.1007/978-3-031-94575-5_20",
language = "Ingl{\'e}s",
isbn = "9783031945748",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "362--382",
editor = "Edward Curry and Maribel Acosta and Maria Poveda-Villal{\'o}n and {van Erp}, Marieke and Adegboyega Ojo and Katja Hose and Cogan Shimizu and Pasquale Lisena",
booktitle = "The Semantic Web - 22nd European Semantic Web Conference, ESWC 2025, Proceedings",
address = "Alemania",
}