DECOMPOSITION OF ONTOLOGIES AND KNOWLEDGE GRAPHS VIA ZERO-ORDER RELATIONS
DOI:
https://doi.org/10.34185/1991-7848.itmm.2026.01.067Keywords:
Knowledge graph, ontology, reification, logical statement decomposition, knowledge representation, neural networksAbstract
Knowledge graphs and ontologies operate with structurally heterogeneous statements – binary triples, n-ary reified relations, and nested facts – which complicates their unified processing. This paper proposes decomposing any ontological statement into a single primitive – an anonymous directed link of zero order (). The predicate is transferred from the edge to a node, producing a homogeneous graph where all ontological elements are nodes connected by a single edge type. The decomposition relies on two principles: role neutrality of concepts, whereby the distinction between «entity» and «relation» is contextual rather than ontological, and recursive statement order, which formalizes structural complexity through a metric. It is shown that -decomposition performs for knowledge graphs a role analogous to tokenization for natural language texts: it transforms a heterogeneous structure into a homogeneous one suitable for neural network processing.
References
Hogan, A., Blomqvist, E., Cochez, M., d'Amato, C., Melo, G. D., Gutierrez, C., ... & Zimmermann, A. (2021). Knowledge graphs. ACM Computing Surveys, 54(4), 1–37. DOI: 10.1145/3447772
Hernández, D., Hogan, A., & Krötzsch, M. (2015). Reifying RDF: What works well with Wikidata? Proceedings of the 11th International Workshop on Scalable Semantic Web Knowledge Base Systems (SSWS), 32–47. URL: https://ceur-ws.org/Vol-1457/SSWS2015_paper3.pdf
Hartig, O. (2017). Foundations of RDF* and SPARQL* — An alternative approach to statement-level metadata in RDF. Proceedings of the 11th Alberto Mendelzon International Workshop on Foundations of Data Management (AMW), vol. 1912. URL: https://ceur-ws.org/Vol-1912/paper12.pdf
Galkin, M., Trivedi, P., Maheshwari, G., Usbeck, R., & Lehmann, J. (2020). Message passing for hyper-relational knowledge graphs. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 7346–7359. DOI: 10.18653/v1/2020.emnlp-main.596
Guan, S., Jin, X., Wang, Y., & Cheng, X. (2019). Link prediction on n-ary relational data. Proceedings of the World Wide Web Conference (WWW), 583–593. DOI: 10.1145/3308558.3313414
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 30. URL: https://papers.nips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
Rosso, P., Yang, D., & Cudré-Mauroux, P. (2020). Beyond triplets: Hyper-relational knowledge graph embedding for link prediction. Proceedings of The Web Conference (WWW), 1885–1896. DOI: 10.1145/3366423.3380257
