Integrating Quantum Machine Learning and Ontology Matching for Efficient Semantic Web Services discovery
- 1Information Technology Department, Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia
Abstract
Existing Semantic Web Service (SWS) discovery approaches based on classical machine learning suffer from limited representational capacity in high-dimensional semantic feature spaces and fail to fully exploit structured ontological knowledge for semantic alignment. This paper addresses these gaps by proposing a hybrid framework that integrates Quantum Machine Learning (QML) models with multi-type Ontology Matching to improve both the accuracy and semantic coverage of SWS discovery. In this paper, we discuss the use of quantum machine learning models and ontological matching techniques for the discovery of Semantic Web Services (SWS) in the Semantic Web. We contrast the effectiveness of different quantum machine learning models with their classical counterparts, including Quantum k-Nearest Neighbors (QkNN), Quantum Decision Trees, Quantum Random Forest, and Quantum Support Vector Machines (QSVM). Our experiments on the OWLS-TC v4 benchmark demonstrate that QSVM achieved the highest post-integration accuracy of 95.1% when paired with graph-based ontology matching, while Quantum Random Forest achieved the highest standalone accuracy of 92.2% without ontology matching. QSVM’s standalone accuracy was 63.0%, reflecting its sensitivity to noisy feature representations in the absence of semantic enrichment; ontology matching consistently recovered and surpassed its performance. Tables 7 through 10 report post-integration results per matching method. Table 13 reports standalone baseline accuracy. These two result sets are distinct and complementary, not contradictory. The application of ontological matching techniques to SWS discovery made the accuracy of SWS discovering much better in both quantum and classical machine learning models. QkNN was the one with the greatest accuracy improvement of 2.8% after adding ontological matching in the mix. Our results indicate that quantum machine learning models, for example Quantum Random Forest (QRF) and Quantum k-Nearest Neighbors (QkNN), are the best candidates for the discovery of SWS. The application of ontological matching methods together with machine learning models is advisable for the improvement of the accuracy of the SWS discovery process. Nevertheless, it should be mentioned that the efficiency of these methods may be different depending on the accuracy and the completeness of the ontologies that are the basis. This research gives a useful information about the possible of quantum machine learning models and ontological matching techniques for enhancing the SWS finding accuracy.
Related
- Constructing the Self Data Atlas ontology: a crisp-fuzzy ontology for quality of life representation in children with neurodevelopmental and learning disabilities
- ICONIC: An R Package for Integrating Instrumental Variable- and Negative-Control-Informed Causal Discovery and Diagnostics in Multiomic Studies
- Redefining drug discovery: AI-driven strategies for efficient cancer therapeutics.
- Integrating disulfidptosis patterns and machine learning identifies a novel diagnostic signature for endometriosis
- Letter to the Editor: Integrating Machine Learning Into Stroke Risk Stratification in AF—Authors' Reply
BibTeX
@article{alatawi2026integrating,
title = {{Integrating Quantum Machine Learning and Ontology Matching for Efficient Semantic Web Services discovery}},
author = {Mohammed Naif Alatawi},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0360079},
url = {https://doi.org/10.1371/journal.pone.0360079},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Integrating Quantum Machine Learning and Ontology Matching for Efficient Semantic Web Services discovery
AU - Mohammed Naif Alatawi
PY - 2026
DA - 2026/10/13
JO - PLOS One
DO - 10.1371/journal.pone.0360079
UR - https://doi.org/10.1371/journal.pone.0360079
AB - Existing Semantic Web Service (SWS) discovery approaches based on classical machine learning suffer from limited representational capacity in high-dimensional semantic feature spaces and fail to fully exploit structured ontological knowledge for semantic alignment. This paper addresses these gaps by proposing a hybrid framework that integrates Quantum Machine Learning (QML) models with multi-type Ontology Matching to improve both the accuracy and semantic coverage of SWS discovery. In this paper, we discuss the use of quantum machine learning models and ontological matching techniques for the discovery of Semantic Web Services (SWS) in the Semantic Web. We contrast the effectiveness of different quantum machine learning models with their classical counterparts, including Quantum k-Nearest Neighbors (QkNN), Quantum Decision Trees, Quantum Random Forest, and Quantum Support Vector Machines (QSVM). Our experiments on the OWLS-TC v4 benchmark demonstrate that QSVM achieved the highest post-integration accuracy of 95.1% when paired with graph-based ontology matching, while Quantum Random Forest achieved the highest standalone accuracy of 92.2% without ontology matching. QSVM’s standalone accuracy was 63.0%, reflecting its sensitivity to noisy feature representations in the absence of semantic enrichment; ontology matching consistently recovered and surpassed its performance. Tables 7 through 10 report post-integration results per matching method. Table 13 reports standalone baseline accuracy. These two result sets are distinct and complementary, not contradictory. The application of ontological matching techniques to SWS discovery made the accuracy of SWS discovering much better in both quantum and classical machine learning models. QkNN was the one with the greatest accuracy improvement of 2.8% after adding ontological matching in the mix. Our results indicate that quantum machine learning models, for example Quantum Random Forest (QRF) and Quantum k-Nearest Neighbors (QkNN), are the best candidates for the discovery of SWS. The application of ontological matching methods together with machine learning models is advisable for the improvement of the accuracy of the SWS discovery process. Nevertheless, it should be mentioned that the efficiency of these methods may be different depending on the accuracy and the completeness of the ontologies that are the basis. This research gives a useful information about the possible of quantum machine learning models and ontological matching techniques for enhancing the SWS finding accuracy.
SN - 1932-6203
ER -