Towards leveraging explicit negative statements in knowledge graph embeddings

Knowledge Graphs are used in various domains to represent knowledge about entities and their relations. In the vast majority of cases, they capture what is known to be true about those entities, i.e., positive statements, while the Open World Assumption implicitly states that everything not expresse...

Full description

Saved in:
Bibliographic Details
Main Authors: Rita T. Sousa, Catia Pesquita, Heiko Paulheim
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Web Semantics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1570826824000374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841545585172152320
author Rita T. Sousa
Catia Pesquita
Heiko Paulheim
author_facet Rita T. Sousa
Catia Pesquita
Heiko Paulheim
author_sort Rita T. Sousa
collection DOAJ
description Knowledge Graphs are used in various domains to represent knowledge about entities and their relations. In the vast majority of cases, they capture what is known to be true about those entities, i.e., positive statements, while the Open World Assumption implicitly states that everything not expressed in the graph may or may not be true. This makes it difficult and less frequent to capture information explicitly known not to be true, i.e., negative statements. Moreover, while those negative statements could bear the potential to learn more useful representations in knowledge graph embeddings, that direction has been explored only rarely. However, in many domains, negative information is particularly interesting, for example, in recommender systems, where negative associations of users and items can help in learning better user representations, or in the biomedical domain, where the knowledge that a patient does exhibit a specific symptom can be crucial for accurate disease diagnosis.In this paper, we argue that negative statements should be given more attention in knowledge graph embeddings. Moreover, we investigate how they can be used in knowledge graph embedding methods, highlighting their potential in some interesting use cases. We discuss some existing works and preliminary results that incorporate explicitly declared negative statements in walk-based knowledge graph embedding methods. Finally, we outline promising avenues for future research in this area.
format Article
id doaj-art-624ad06818e24279bd2d1742ac85f90d
institution Kabale University
issn 1570-8268
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Web Semantics
spelling doaj-art-624ad06818e24279bd2d1742ac85f90d2025-01-12T05:24:31ZengElsevierWeb Semantics1570-82682025-01-0184100851Towards leveraging explicit negative statements in knowledge graph embeddingsRita T. Sousa0Catia Pesquita1Heiko Paulheim2Data and Web Science Group, University of Mannheim, Mannheim, Germany; Corresponding author.LASIGE, University of Lisbon, Lisbon, PortugalData and Web Science Group, University of Mannheim, Mannheim, GermanyKnowledge Graphs are used in various domains to represent knowledge about entities and their relations. In the vast majority of cases, they capture what is known to be true about those entities, i.e., positive statements, while the Open World Assumption implicitly states that everything not expressed in the graph may or may not be true. This makes it difficult and less frequent to capture information explicitly known not to be true, i.e., negative statements. Moreover, while those negative statements could bear the potential to learn more useful representations in knowledge graph embeddings, that direction has been explored only rarely. However, in many domains, negative information is particularly interesting, for example, in recommender systems, where negative associations of users and items can help in learning better user representations, or in the biomedical domain, where the knowledge that a patient does exhibit a specific symptom can be crucial for accurate disease diagnosis.In this paper, we argue that negative statements should be given more attention in knowledge graph embeddings. Moreover, we investigate how they can be used in knowledge graph embedding methods, highlighting their potential in some interesting use cases. We discuss some existing works and preliminary results that incorporate explicitly declared negative statements in walk-based knowledge graph embedding methods. Finally, we outline promising avenues for future research in this area.http://www.sciencedirect.com/science/article/pii/S1570826824000374Knowledge graphKnowledge graph embeddingNegative statements
spellingShingle Rita T. Sousa
Catia Pesquita
Heiko Paulheim
Towards leveraging explicit negative statements in knowledge graph embeddings
Web Semantics
Knowledge graph
Knowledge graph embedding
Negative statements
title Towards leveraging explicit negative statements in knowledge graph embeddings
title_full Towards leveraging explicit negative statements in knowledge graph embeddings
title_fullStr Towards leveraging explicit negative statements in knowledge graph embeddings
title_full_unstemmed Towards leveraging explicit negative statements in knowledge graph embeddings
title_short Towards leveraging explicit negative statements in knowledge graph embeddings
title_sort towards leveraging explicit negative statements in knowledge graph embeddings
topic Knowledge graph
Knowledge graph embedding
Negative statements
url http://www.sciencedirect.com/science/article/pii/S1570826824000374
work_keys_str_mv AT ritatsousa towardsleveragingexplicitnegativestatementsinknowledgegraphembeddings
AT catiapesquita towardsleveragingexplicitnegativestatementsinknowledgegraphembeddings
AT heikopaulheim towardsleveragingexplicitnegativestatementsinknowledgegraphembeddings