Enregistré dans:
Détails bibliographiques
Auteur principal: Jing, Yonglin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.15140
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910350034599936
author Jing, Yonglin
author_facet Jing, Yonglin
contents Hyper-relational knowledge graphs (KGs) contain additional key-value pairs, providing more information about the relations. In many scenarios, the same relation can have distinct key-value pairs, making the original triple fact more recognizable and specific. Prior studies on hyper-relational KGs have established a solid standard method for hyper-relational graph encoding. In this work, we propose a message-passing-based graph encoder with global relation structure awareness ability, which we call ReSaE. Compared to the prior state-of-the-art approach, ReSaE emphasizes the interaction of relations during message passing process and optimizes the readout structure for link prediction tasks. Overall, ReSaE gives a encoding solution for hyper-relational KGs and ensures stronger performance on downstream link prediction tasks. Our experiments demonstrate that ReSaE achieves state-of-the-art performance on multiple link prediction benchmarks. Furthermore, we also analyze the influence of different model structures on model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15140
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Relation-Interactive Approach for Message Passing in Hyper-relational Knowledge Graphs
Jing, Yonglin
Artificial Intelligence
Hyper-relational knowledge graphs (KGs) contain additional key-value pairs, providing more information about the relations. In many scenarios, the same relation can have distinct key-value pairs, making the original triple fact more recognizable and specific. Prior studies on hyper-relational KGs have established a solid standard method for hyper-relational graph encoding. In this work, we propose a message-passing-based graph encoder with global relation structure awareness ability, which we call ReSaE. Compared to the prior state-of-the-art approach, ReSaE emphasizes the interaction of relations during message passing process and optimizes the readout structure for link prediction tasks. Overall, ReSaE gives a encoding solution for hyper-relational KGs and ensures stronger performance on downstream link prediction tasks. Our experiments demonstrate that ReSaE achieves state-of-the-art performance on multiple link prediction benchmarks. Furthermore, we also analyze the influence of different model structures on model performance.
title A Relation-Interactive Approach for Message Passing in Hyper-relational Knowledge Graphs
topic Artificial Intelligence
url https://arxiv.org/abs/2402.15140