{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:04:54Z","timestamp":1784203494855,"version":"3.55.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>Hierarchical data is common in many domains like life sciences and e-commerce, and its embeddings often play a critical role. \nWhile hyperbolic embeddings offer a theoretically grounded approach to representing hierarchies in low-dimensional spaces, current methods often rely on specific geometric constructs as embedding candidates. This reliance limits their generalizability and makes it difficult to integrate with techniques that model semantic relationships beyond pure hierarchies, such as ontology embeddings. \nIn this paper, we present RegD, a flexible Euclidean framework that supports the use of arbitrary geometric regions-such as boxes and balls-as embedding representations. Although RegD operates entirely in Euclidean space, we formally prove that it achieves hyperbolic-like expressiveness by incorporating a depth-based dissimilarity between regions, enabling it to emulate key properties of hyperbolic geometry, including exponential growth. \nWe establish the faithfulness of our approach. Furthermore, extensive empirical evaluations on diverse real-world datasets demonstrate consistent performance improvements over state-of-the-art methods, highlighting RegD\u2019s potential for broader applications, including ontology embedding tasks that extend beyond hierarchical structures.<\/jats:p>","DOI":"10.24963\/kr.2026\/110","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:15:53Z","timestamp":1784200553000},"page":"1170-1181","source":"Crossref","is-referenced-by-count":0,"title":["RegD: Hierarchical Embeddings via Dissimilarity between Arbitrary Euclidean Regions"],"prefix":"10.24963","author":[{"given":"Hui","family":"Yang","sequence":"first","affiliation":[{"name":"University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaoyan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Manchester"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"23nd International Conference on Principles of Knowledge Representation and Reasoning {KR-2026}","theme":"Artificial Intelligence","location":"Lisbon, Portuagal","acronym":"KR-2026","number":"23","sponsor":["Artificial Intelligence Journal","Principles of Knowledge Representation and Reasoning Inc.","European Association for Artificial Intelligence"],"start":{"date-parts":[[2026,7,20]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["Proceedings of the TwentyThird International Conference on Principles of Knowledge Representation and Reasoning"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:16:22Z","timestamp":1784200582000},"score":1,"resource":{"primary":{"URL":"https:\/\/proceedings.kr.org\/2026\/110"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/kr.2026\/110","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}