|
Do similar entities have similar embeddings?
Hubert, Nicolas
;
Paulheim, Heiko
;
Brun, Armelle
;
Monticolo, Davy
|
DOI:
|
https://doi.org/10.1007/978-3-031-60626-7_1
|
|
URL:
|
https://link.springer.com/chapter/10.1007/978-3-03...
|
|
Document Type:
|
Conference or workshop publication
|
|
Year of publication:
|
2024
|
|
Book title:
|
The Semantic Web : 21st International Conference, ESWC 2024, Hersonissos, Crete, Greece, May 26-30, 2024, Proceedings. Part I
|
|
The title of a journal, publication series:
|
Lecture Notes in Computer Science
|
|
Volume:
|
14664
|
|
Page range:
|
3-21
|
|
Conference title:
|
ESWC 2024, Extended Semantic Web Conference
|
|
Location of the conference venue:
|
Hersonissos, Crete, Greece
|
|
Date of the conference:
|
26.-30.05.2024
|
|
Publisher:
|
Albert, Meroño Peñuela
;
Dimou, Anastasia
;
Troncy, Raphaël
;
Hartig, Olaf
;
Acosta, Maribel
;
Alam, Mehwish
;
Paulheim, Heiko
;
Lisena, Pasquale
|
|
Place of publication:
|
Berlin [u.a.]
|
|
Publishing house:
|
Springer
|
|
ISSN:
|
0302-9743 , 1611-3349
|
|
Publication language:
|
English
|
|
Institution:
|
School of Business Informatics and Mathematics > Data Science (Paulheim 2018-)
|
|
Subject:
|
004 Computer science, internet
|
|
Abstract:
|
Knowledge graph embedding models (KGEMs) developed for link prediction learn vector representations for entities in a knowledge graph, known as embeddings. A common tacit assumption is the KGE entity similarity assumption, which states that these KGEMs retain the graph’s structure within their embedding space, i.e., position similar entities within the graph close to one another. This desirable property make KGEMs widely used in downstream tasks such as recommender systems or drug repurposing. Yet, the relation of entity similarity and similarity in the embedding space has rarely been formally evaluated. Typically, KGEMs are assessed based on their sole link prediction capabilities, using ranked-based metrics such as Hits@K or Mean Rank. This paper challenges the prevailing assumption that entity similarity in the graph is inherently mirrored in the embedding space. Therefore, we conduct extensive experiments to measure the capability of KGEMs to cluster similar entities together, and investigate the nature of the underlying factors. Moreover, we study if different KGEMs expose a different notion of similarity.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 Search Authors in
BASE:
Hubert, Nicolas
;
Paulheim, Heiko
;
Brun, Armelle
;
Monticolo, Davy
Google Scholar:
Hubert, Nicolas
;
Paulheim, Heiko
;
Brun, Armelle
;
Monticolo, Davy
ORCID:
Hubert, Nicolas ; Paulheim, Heiko  ORCID: 0000-0003-4386-8195 ; Brun, Armelle ; Monticolo, Davy
["search_editors_ORCID" not defined]
Albert, Meroño Peñuela ; Dimou, Anastasia ; Troncy, Raphaël ; Hartig, Olaf ; Acosta, Maribel ; Alam, Mehwish ; Paulheim, Heiko ORCID: 0000-0003-4386-8195 ; Lisena, Pasquale
You have found an error? Please let us know about your desired correction here: E-Mail
Actions (login required)
 |
Show item |
|
