DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights

Knowledge graphs (KGs) possess a vital role in enhancing the semantic comprehension of extensive datasets across many fields. It facilitate activities like recommendation systems, semantic searching, and intelligent data mining. However, lacking information can sometimes limit the usefulness of know...

Full description

Saved in:
Bibliographic Details
Main Authors: Haji Gul, Feras Al-Obeidat, Adnan Amin, Muhammad Wasim, Fernando Moreira
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10756593/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126938324074496
author Haji Gul
Feras Al-Obeidat
Adnan Amin
Muhammad Wasim
Fernando Moreira
author_facet Haji Gul
Feras Al-Obeidat
Adnan Amin
Muhammad Wasim
Fernando Moreira
author_sort Haji Gul
collection DOAJ
description Knowledge graphs (KGs) possess a vital role in enhancing the semantic comprehension of extensive datasets across many fields. It facilitate activities like recommendation systems, semantic searching, and intelligent data mining. However, lacking information can sometimes limit the usefulness of knowledge graphs (KGs), as the lack of relationships between entities could severely limit their practical application. Most existing approaches for KG completion primarily concentrate on embedding-based methods or just use relational paths, neglecting the valuable structural information offered by node density. This research presents an approach that effectively combines relational paths and the density features of tail nodes to enhance the accuracy of predicting relationships that are missing in knowledge graphs. Our method combines the sequential relational context represented by paths with the structural prominence indicated by node density, allowing for a dual view on possible entity connections. We validate the effectiveness of our technique by conducting comprehensive tests on many benchmark datasets, revealing substantial enhancements compared to conventional approaches. The Dual-Rep model, which incorporates relational paths and node density features, has continuously shown improved performance across several metrics, such as Mean Reciprocal Rank (MRR), Hit at 1 (Hit@1), and Hit at 3 (Hit@3). The DualRep model achieved a mean reciprocal rank (MRR) of 90.80. Additionally, it achieved a hit rate of 87.39 at rank 1 (Hit@1) and a hit rate of 91.18.
format Article
id doaj-art-c29c595d222d4d4ba37f6a3a9be85392
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c29c595d222d4d4ba37f6a3a9be853922025-08-20T02:33:48ZengIEEEIEEE Access2169-35362024-01-011217956617957810.1109/ACCESS.2024.350173510756593DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density InsightsHaji Gul0https://orcid.org/0000-0002-2227-6564Feras Al-Obeidat1https://orcid.org/0000-0001-6941-6555Adnan Amin2Muhammad Wasim3https://orcid.org/0000-0003-4154-105XFernando Moreira4https://orcid.org/0000-0002-0816-1445School of Digital Science, Universiti Brunei Darussalam, Bandar Seri Begawan, BruneiCollege of Technological Innovation, Zayed University, Abu Dhabi, United Arab EmiratesSchool of Computer Science and Information Technology, Institute of Management Sciences Peshawar, Peshawar, PakistanDepartment of Computer Science, City University of Science and Information Technology, Peshawar, PakistanREMIT, IJP, Universidade Portucalense, Porto, PortugalKnowledge graphs (KGs) possess a vital role in enhancing the semantic comprehension of extensive datasets across many fields. It facilitate activities like recommendation systems, semantic searching, and intelligent data mining. However, lacking information can sometimes limit the usefulness of knowledge graphs (KGs), as the lack of relationships between entities could severely limit their practical application. Most existing approaches for KG completion primarily concentrate on embedding-based methods or just use relational paths, neglecting the valuable structural information offered by node density. This research presents an approach that effectively combines relational paths and the density features of tail nodes to enhance the accuracy of predicting relationships that are missing in knowledge graphs. Our method combines the sequential relational context represented by paths with the structural prominence indicated by node density, allowing for a dual view on possible entity connections. We validate the effectiveness of our technique by conducting comprehensive tests on many benchmark datasets, revealing substantial enhancements compared to conventional approaches. The Dual-Rep model, which incorporates relational paths and node density features, has continuously shown improved performance across several metrics, such as Mean Reciprocal Rank (MRR), Hit at 1 (Hit@1), and Hit at 3 (Hit@3). The DualRep model achieved a mean reciprocal rank (MRR) of 90.80. Additionally, it achieved a hit rate of 87.39 at rank 1 (Hit@1) and a hit rate of 91.18.https://ieeexplore.ieee.org/document/10756593/Knowledge graph completionrelational pathsnode density analysisgraph structural featuresentity relationship predictiongraph neural networks
spellingShingle Haji Gul
Feras Al-Obeidat
Adnan Amin
Muhammad Wasim
Fernando Moreira
DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
IEEE Access
Knowledge graph completion
relational paths
node density analysis
graph structural features
entity relationship prediction
graph neural networks
title DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
title_full DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
title_fullStr DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
title_full_unstemmed DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
title_short DualRep: Knowledge Graph Completion by Utilizing Dual Representation of Relational Paths and Tail Node Density Insights
title_sort dualrep knowledge graph completion by utilizing dual representation of relational paths and tail node density insights
topic Knowledge graph completion
relational paths
node density analysis
graph structural features
entity relationship prediction
graph neural networks
url https://ieeexplore.ieee.org/document/10756593/
work_keys_str_mv AT hajigul dualrepknowledgegraphcompletionbyutilizingdualrepresentationofrelationalpathsandtailnodedensityinsights
AT ferasalobeidat dualrepknowledgegraphcompletionbyutilizingdualrepresentationofrelationalpathsandtailnodedensityinsights
AT adnanamin dualrepknowledgegraphcompletionbyutilizingdualrepresentationofrelationalpathsandtailnodedensityinsights
AT muhammadwasim dualrepknowledgegraphcompletionbyutilizingdualrepresentationofrelationalpathsandtailnodedensityinsights
AT fernandomoreira dualrepknowledgegraphcompletionbyutilizingdualrepresentationofrelationalpathsandtailnodedensityinsights