Supervised knowledge aggregation for knowledge graph completion


Betz, Patrick ; Meilicke, Christian ; Stuckenschmidt, Heiner



DOI: https://doi.org/10.1007/978-3-031-06981-9_5
URL: https://link.springer.com/chapter/10.1007/978-3-03...
Additional URL: https://2022.eswc-conferences.org/wp-content/uploa...
Document Type: Conference or workshop publication
Year of publication: 2022
Book title: The semantic web: 19th International Conference, ESWC 2022, Hersonissos, Crete, Greece, May 29-June 2, 2022 : proceedings
The title of a journal, publication series: Lecture Notes in Computer Science
Page range: 74-92
Conference title: ESWC 2022
Location of the conference venue: Hersonissos, Greece
Date of the conference: 29.05.-02.06.2022
Publisher: Groth, Paul
Place of publication: Berlin [u.a.]
Publishing house: Springer
ISBN: 978-3-031-06980-2 , 978-3-031-06981-9
ISSN: 0302-9743 , 1611-3349
Publication language: English
Institution: School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Subject: 004 Computer science, internet
Abstract: We explore data-driven rule aggregation based on latent feature representations in the context of knowledge graph completion. For a given query and a collection of rules obtained by a symbolic rule learning system, we propose end-to-end trainable aggregation functions for combining the rules into a confidence score answering the query. Despite using latent feature representations for rules, the proposed models remain fully interpretable in terms of the underlying symbolic approach. While our models improve the base learner constantly and achieve competitive results on various benchmark knowledge graphs, we outperform current state-of-the-art with respect to a biomedical knowledge graph by a significant margin. We argue that our approach is in particular well suited for link prediction tasks dealing with a large multi-relational knowledge graph with several million triples, while the queries of interest focus on only one specific target relation.




Dieser Eintrag ist Teil der Universitätsbibliographie.




Metadata export


Citation


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item