{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:03:54Z","timestamp":1764842634014},"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":[[2022,7]]},"abstract":"<jats:p>For many years, link prediction on knowledge. graphs has been a purely transductive task, not allowing for reasoning on unseen entities. \n\nRecently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities.\n\nStill, all these approaches only consider triple-based KGs, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied.\n\nIn this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. \n\nOur experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines. \n\nOur code is available at https:\/\/github.com\/mali-git\/hyper_relational_ilp.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/731","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"5259-5263","source":"Crossref","is-referenced-by-count":3,"title":["Improving Inductive Link Prediction Using Hyper-Relational Facts (Extended Abstract)"],"prefix":"10.24963","author":[{"given":"Mehdi","family":"Ali","sequence":"first","affiliation":[{"name":"Fraunhofer IAIS, Smart Data Analytics Group, University of Bonn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Berrendorf","sequence":"additional","affiliation":[{"name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikhail","family":"Galkin","sequence":"additional","affiliation":[{"name":"Mila, McGill University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veronika","family":"Thost","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengfei","family":"Ma","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[{"name":"Siemens, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jens","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Fraunhofer IAIS, Smart Data Analytics Group, University of Bonn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2022","name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","start":{"date-parts":[[2022,7,23]]},"theme":"Artificial Intelligence","location":"Vienna, Austria","end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:11:19Z","timestamp":1658142679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/731"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/731","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}