Alignment of Ontologies Using Directed Graphs, Neural Network and Genetic Algorithm in the Web of Data

Semantic interoperability remains a central challenge for the Semantic Web, as the growth of structured data increases the need to reconcile heterogeneous ontologies across domains such as education, health, defence, agriculture and biomedicine. This paper proposes a hybrid ontology-alignment architecture that combines directed-graph representations to capture semantic and taxonomic structure, graph neural networks (GNNs) enriched with BioBERT embeddings to learn latent semantic correspondences, and a genetic algorithm to optimise the final selection of matches under structural-consistency constraints. The approach is illustrated on the biomedical domain, where reference ontologies such as SNOMED CT, ICD-10 and LOINC are large, complex and structurally rich, and where aligning hospital data with such reference terminologies supports interoperability and diagnostic assistance. Simulated experiments inspired by the OAEI Anatomy and LargeBio benchmarks indicate that combining the three layers improves the F-measure relative to each layer taken in isolation, primarily by reducing false positives through structural filtering. A component-wise ablation study isolates the contribution of each layer, and the simulated results are positioned, for indicative purposes only, against published OAEI systems. A complementary, non-simulated evaluation on the actual small LargeBio ontology fragments (FMA–NCI, FMA–SNOMED, SNOMED–NCI), scored locally with a MELT-style evaluator, shows the hybrid pipeline reaching the best precision of all matcher variants on every pair but not the best F-measure, since it trades recall away more than it recovers, a real-data finding that qualifies the simulated ablation and points to blocking-width and fitness-weight calibration as concrete next steps. The paper also identifies the remaining methodological steps an official OAEI submission under SEALS/MELT, an equivalent run on Anatomy, statistical validation across multiple seeds, and a dedicated scalability study required to move from illustrative simulation to a fully validated system.

ontology alignment, machine learning, ontologies, neural networks, genetic algorithms, data graphs, GNN, biomedical interoperability, BioBERT, patient monitoring.

1. Jean-François Djoufak-Kengue, Jérôme Euzenat, Petko Valtchev. Alignment of ontologies structure-driven. Proceedings of the 14th National Days on Languages and Object Models (LMO), March 2008, Montreal, Canada, pp.43-57, 2008 . [Google Scholar] [Crossref]

2. Yassine Namir et al. Alignment of semantic web ontologies. 2016. [Google Scholar] [Crossref]

3. Mariem Mahfoudh. Adapting ontologies with standard graph grammars: evolution and merger. Other [cs.OH]. Université de Haute-Alsace Mulhouse, 2015. NNT: 2015MULH1519, tel-01528579. [Google Scholar] [Crossref]

4. Ramdane Ahmed Merouane. Alignment of domain ontologies. 2019. [Google Scholar] [Crossref]

5. Catherine Roussey et al. Ontologies in agriculture. 2015. [Google Scholar] [Crossref]

6. Michel Héon. Semantic Web and Ontological Modeling with G-OWL: Java Developer's Guide Eclipse. Université du Québec à Montréal, 2014. [Google Scholar] [Crossref]

7. Corcho O., Fernández-López M., Gómez-Pérez A. Methodologies, tools and languages for building ontologies: where is their meeting point? Data and Knowledge Engineering, vol. 46, n°1, 2003, pp. 41-64. https://doi.org/10.1016/S0169-023X(02)00195-7 [Google Scholar] [Crossref]

8. Berners-Lee, T. (2001). The Semantic Web. Scientific American, 284(5), 35-43. https://doi.org/10.1038/scientificamerican0501-34 [Google Scholar] [Crossref]

9. Kaladzavi et al. (2018). Assessing similarity value between two ontologies. [Google Scholar] [Crossref]

10. Noy, N., Fergerson, R. W., Musen, M. A. (2000). The knowledge model of Protégé2000: combining interoperability and flexibility. Proceedings of the International Conference on Knowledge Engineering and Knowledge Management (EKAW'00). https://doi.org/10.1007/3-540-39967-4_2 [Google Scholar] [Crossref]

11. Euzenat, J., Shvaiko, P. (2007). Ontology Matching. Springer-Verlag, Heidelberg (DE). https://doi.org/10.1007/978-3-540-49612-0 [Google Scholar] [Crossref]

12. Euzenat, J. (2001). Towards a principled approach to semantic interoperability. Proceedings of the IJCAI Workshop on Ontology and Information Sharing, pp. 19-25, Seattle, US. [Google Scholar] [Crossref]

13. Euzenat, J., Bach, T.L., Barrasa, J., Bouquet, P., Bo, J.D., Dieng-Kuntz, R., Ehrig, M., Hauswirth, M., Jarrar, M., Lara, R., Maynard, D., Napoli, A., Stamou, G. (2006). State of the art on ontology matching. Deliverable, Knowledge Web NoE. [Google Scholar] [Crossref]

14. Stuckenschmidt, H., Shvaiko, P., Tessaris, S., Àcker, S.V., Zaihrayeu, I. (2004). State of the art on ontology alignment. Deliverable 2.2.3, IST Knowledge Web NoE, 80p., June 2004. [Google Scholar] [Crossref]

15. Amir Laadhar. Local matching learning of large scale biomedical ontologies. Technology for Human Learning. Université Paul Sabatier Toulouse III, 2019. NNT: 2019TOU30126. [Google Scholar] [Crossref]

16. Shvaiko, P., Euzenat, J. (2007). A survey of schema-based matching approaches. Journal on Data Semantics. https://doi.org/10.1007/11603412_5 [Google Scholar] [Crossref]

17. Jaro, M. A. (1995). Probabilistic linkage of large public health data files. Statistics in Medicine, 14, 491-498. https://doi.org/10.1002/sim.4780140510 [Google Scholar] [Crossref]

18. Khiat, Abderrahmane (2017). Developing an environment for ontology alignment: an instance-based approach. [Google Scholar] [Crossref]

19. Abdoulaye Diallo, Mouhamadou Thiam. State of the art on ontology alignment. 2021. hal-03330388. [Google Scholar] [Crossref]

20. Saadi, I., Bordji, Z. (2024). Systematic review of the literature on machine-learning methods for big data analysis, with a case study (Doctoral dissertation, University BBA). [Google Scholar] [Crossref]

21. Dilekh, Tahar (2019). A semantic model for Arabic language information retrieval. Ph.D. thesis, University of Batna 2. [Google Scholar] [Crossref]

22. Amin, M. B., Khan, W. A., Lee, S., Kang, B. H. (2015). Performance-based ontology matching: a data-parallel approach for effectiveness-independent performance gain in ontology matching. Applied Intelligence, 43, 356-385. [Google Scholar] [Crossref]

23. Achichi, Manel et al. Results of the Ontology Alignment Evaluation Initiative 2016. OM: Ontology Matching, no. 1766, 2016. [Google Scholar] [Crossref]

24. Hong, J. L., Siew, E. G., Egerton, S. (2010, May). Aligning data records using WordNet. In 2010 Second International Conference on Computer Research and Development, pp. 56-60. IEEE. https://doi.org/10.1109/ICCRD.2010.79 [Google Scholar] [Crossref]

25. Alasoud, A., Haarslev, V., Shiri, N. (2007). A multi-level matching algorithm for combining similarity measures in ontology integration. In Ontologies-Based Databases and Information Systems, pp. 1-17. Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-68123-6_63 [Google Scholar] [Crossref]

26. He, Y., Chen, J., Dong, H., Horrocks, I., Allocca, C., Kim, T., Sapkota, B. (2024). DeepOnto: a Python package for ontology engineering with deep learning. Semantic Web, 15(5), 1991-2004. https://doi.org/10.3233/SW-243568 [Google Scholar] [Crossref]

27. Li, N., Bailleux, T., Bouraoui, Z., Schockaert, S. (2024). Ontology completion with natural language inference and concept embeddings: an analysis. arXiv:2403.17216. https://doi.org/10.1016/j.websem.2006.05.003 [Google Scholar] [Crossref]

28. Ring, J. (2009). Evolving an autonomous test and evaluation enterprise. [Google Scholar] [Crossref]

29. Lambrix, P., Tan, H. (2006). SAMBO a system for aligning and merging biomedical ontologies. Journal of Web Semantics, 4(3), 196-206. [Google Scholar] [Crossref]

30. Stucky, B., Luc, A. (2017). OntoPilot: new software to simplify and accelerate ontology development and deployment. Biodiversity Information Science and Standards. [Google Scholar] [Crossref]

31. Zaoui, Sayah (2023). Integration of semantics in big data. Doctoral thesis, Kasdi Merbah Ouargla University. [Google Scholar] [Crossref]

32. Sourty, Raphaël (2023). Learning to represent knowledge graphs and enriching language models pre-trained by knowledge graphs: distillation-based approaches. Doctoral thesis, Université Paul Sabatier Toulouse III. [Google Scholar] [Crossref]

33. Algergawy, A., Faria, D., Ferrara, A., Fundulaki, I., Harrow, I., Hertling, S., Jiménez-Ruiz, E., Karam, N., Khiat, A., Lambrix, P., Li, H., Montanelli, S., Paulheim, H., Pesquita, C., Saveta, T., Shvaiko, P., Splendiani, A., Thiéblin, É., Trojahn, C., Vatascinová, J., Zamazal, O., Zhou, L. Results of the Ontology Alignment Evaluation Initiative 2019. OM@ISWC, CEUR Workshop Proceedings, vol. 2536, pp. 46-85, 2019. [Google Scholar] [Crossref]

34. Li, H., Li, Y., Michel, F., Nasr, E., Paulheim, H., Pesquita, C., Portisch, J., Roussey, C., Saveta, T., Shvaiko, P., Splendiani, A., Trojahn, C., Vatascinová, J., Yaman, B., Zamazal, O., Zhou, L. Results of the Ontology Alignment Evaluation Initiative 2021. OM@ISWC, CEUR Workshop Proceedings, vol. 3063, pp. 62-108, 2021. [Google Scholar] [Crossref]

35. Algergawy, A. et al. Results of the Ontology Alignment Evaluation Initiative 2019. [Google Scholar] [Crossref]

36. Li, H. et al. Results of the Ontology Alignment Evaluation Initiative 2021. [Google Scholar] [Crossref]

37. Pour, M. A. N., Blomqvist, E., Cotovio, P. G., Coulet, A., Ferraz, L., Hertling, S., Jain, S., Jiménez-Ruiz, E., Kraus, F., Lambrix, P., Li, H., Li, Y., Liu, X., Monnin, P., Paulheim, H., Pesquita, C., Sharma, A., Shvaiko, P., Silva, M. et al. Results of the Ontology Alignment Evaluation Initiative 2025. OM@ISWC, CEUR Workshop Proceedings, 2025. https://doi.org/10.5445/IR/1000189514 [Google Scholar] [Crossref]

38. OAEI 2014 Large BioMed Track results. Ontology Alignment Evaluation Initiative, 2014. [Google Scholar] [Crossref]

39. Mohammadi, M., Atashin, A. A., Hofman, W., Tan, Y.-H. SANOM results for OAEI 2019. OM@ISWC, CEUR Workshop Proceedings, vol. 2536, pp. 178-186, 2019. https://doi.org/10.48550/arXiv.2006.05219 [Google Scholar] [Crossref]

40. Beltagy, I., Lo, K., Cohan, A. (2019). SciBERT: A Pretrained Language Model for Scientific Text. Proceedings of EMNLP-IJCNLP 2019, pp. 3615-3620, Hong Kong. Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1371 [Google Scholar] [Crossref]

41. Yasunaga, M., Leskovec, J., Liang, P. (2022). LinkBERT: Pretraining Language Models with Document Links. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 8003-8016, Dublin, Ireland. (Biomedical variant released as BioLinkBERT.) https://doi.org/10.18653/v1/2022.acl-long.551 [Google Scholar] [Crossref]

42. Djimramadji, J., Warda, L., Mamai, K. A., Mbainaibeye, J., Kaladzavi, G., Kolyang (2025). Hidden Markov Model framework for knowledge correspondence discovery and semantic interoperability across ontologies. International Journal of Knowledge and Innovation Studies, 3(3), 191-200. https://doi.org/10.56578/ijkis030305 [Google Scholar] [Crossref]

43. Mamai, K. A., Warda, L., Kaladzavi, G., Kolyang (2026). Ontologies alignment towards a hybrid approach: a state of the art. Journal of Information Technology and Computer Science (JITCS), 1(2), 1-11. Nicomarc International Publishers. https://doi.org/10.5281/zenodo.2279623 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet