Comparative Analysis of Vector, Graph and Hybrid Models of Knowledge Representation in Information Retrieval Systems
DOI:
https://doi.org/10.52575/2687-0932-2026-53-2-388-399Keywords:
information retrieval, vector models, knowledge graphs, graph models, semantic embeddings, hybrid models, neural network architecturesAbstract
The paper presents the results of an analysis of modern approaches to information retrieval based on vector and graph models of knowledge representation. The advantages and limitations of each approach are identified, including issues of interpretability, scalability, and knowledge completeness. Particular attention is given to hybrid methods that combine the semantic depth of vector representations with the precision of structured graph knowledge. It is shown that hybrid approaches demonstrate high potential for improving search relevance; however, they require further development of a universal methodology for integrating heterogeneous representations. The authors provide practical recommendations for the development and improvement of hybrid models based on the analysis. The study also emphasizes that the effectiveness of such systems depends on data preprocessing, consistent links between entities and the choice of ranking algorithms. These conclusions can support the design of search systems that require deep contextual understanding.
Downloads
References
Список литературы
Абрамович Р.К., Добрынин В.Ю., Платонов А.В. 2025. Объединение глубоких моделей и разреженных представлений в информационном поиске: обзор и анализ современных подходов. Информационные и математические технологии в науке и управлении, 2(38): 5–17. DOI:10.25729/ESI.2025.38.2.001.
Настасенко С.А., Савотченко С.Е. 2025. Гибридный метод поиска в текстовых данных с использованием графов и эмбеддингов. Новые идеи в науках о Земле. Москва: Российский государственный геологоразведочный университет им. Серго Орджоникидзе, 148–151.
Настасенко С.А., Савотченко С.Е. 2025. Интеграция графовых структур в эмбенддинги векторных баз данных для повышения семантического поиска. Донецкие чтения – 2025: образование, наука, инновации, культура и вызовы современности. Донецк: Изд-во ДонГУ, 1: 222–224. EDN: NUFFAH
Chang Y., Wang, X., Wang J., Wu Y., Yang L., Zhu K., Xie X. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology, 15(3), 1–45.
Chao Li, Hao Xu, Kun He, (2024). Meta-multigraph search: Rethinking meta-structure on heterogeneous information networks, Knowledge-Based Systems, 289:111524. https://doi.org/10.1016/j.knosys.2024.111524.
Chatterjee S., Dalton J. 2025. QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking. Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval: 2255–2265. https://doi.org/10.1145/3726302.3730065.
Devlin J., Chang M.-W., Lee, K., Toutanova K. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1: 4171–4186. https://doi.org/10.18653/v1/N19-1423.
Kruhlov, V., Bobos, O., Hnylianska, O., Rossikhin, V., & Kolomiiets, Y. 2024. The Role of Using Artificial Intelligence for Improving the Public Service Provision and Fraud Prevention. Pakistan Journal of Criminology, 16(2): 913–928.
Kyurkchiev P, Iliev A, Kyurkchiev N. 2026. Semantic Search for System Dynamics Models Using Vector Embeddings in a Cloud Microservices Environment. Future Internet, 18(2):86. https://doi.org/10.3390/fi18020086.
Pan Y., Wang L. 2024. Retrieval-Augmented Generation for Code Summarization via Hybrid GNN. IEEE Trans. Softw. Eng. 50: 1234–1250.
Papageorgiou G, Sarlis V, Maragoudakis M, Tjortjis C. 2025. Hybrid Multi-Agent GraphRAG for E-Government: Towards a Trustworthy AI Assistant. Applied Sciences. 15(11): 6315. https://doi.org/10.3390/app15116315
Papageorgiou G, Sarlis V, Maragoudakis M, Tjortjis C. 2025. A Multimodal Framework Embedding Retrieval-Augmented Generation with MLLMs for Eurobarometer Data. AI. 6(3): 50. https://doi.org/10.3390/ai6030050
Raj M., Mishra, N. 2025. Exploring new Approaches for Information Retrieval through Natural Language Processing, arXiv e-prints, Art. no. arXiv:2505.02199, doi:10.48550/arXiv.2505.02199.
Sadykova T., Sinchev B., Young I. C., Auyezova А. 2025. The application of vector space models in intelligent information retrieval systems. Academic Scientific Journal of Computer Science, 355(3), 160–175. https://doi.org/10.32014/2025.2518-1726.370
Sarmah B., Hall B., Rao R., Patel S., Pasquali S., Mehta D. 2024. HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction. arXiv preprint arXiv:2408.04948.
Scarselli F., Gori M., Tsoi A.C., Hagenbuchner M., Monfardini G. 2009. The Graph Neural Network Model. IEEE Trans. Neural Netw. 20, 61–80. https://doi.org/10.1109/TNN.2008.2005605
Zhu X., Guo X., Cao S., Li S., Gong J. 2024. StructuGraphRAG: Structured document-informed knowledge graphs for retrieval-augmented generation. In Proceedings of the AAAI symposium series. 4(1): 242–251.
References
Abramovich R.K., Dobrynin V.YU., Platonov A.V. 2025. Ob'edinenie glubokih modelej i razrezhennyh predstavlenij v informacionnom poiske: obzor i analiz sovremennyh podhodov [Combining deep models and sparse representations in information retrieval: A review and analysis of modern approaches]. Informacionnye i matematicheskie tekhnologii v nauke i upravlenii, 2(38) 5–17. DOI:10.25729/ESI.2025.38.2.001.
Nastasenko S.A., Savotchenko S.E. 2025. Gibridnyj metod poiska v tekstovyh dannyh s ispol'zovaniem grafov i embeddingov [A Hybrid Method for Searching Text Data Using Graphs and Embeddings]. Novye idei v naukah o Zemle. Moskva: Rossijskij gosudarstvennyj geologorazvedochnyj universitet im. Sergo Ordzhonikidze, 148–151.
Nastasenko S.A., Savotchenko S.E. 2025. Integraciya grafovyh struktur v embenddingi vektornyh baz dannyh dlya povysheniya semanticheskogo poiska [Integrating graph structures into vector database embeddings to improve semantic search]. Doneckie chteniya – 2025: obrazovanie, nauka, innovacii, kul'tura i vyzovy sovremennosti. Doneck: Izd-vo DonGU, 1: 222–224. EDN: NUFFAH
Chang Y., Wang X., Wang J., Wu Y., Yang L., Zhu K., Xie X. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology, 15(3), 1–45.
Chao Li, Hao Xu, Kun He, (2024). Meta-multigraph search: Rethinking meta-structure on heterogeneous information networks, Knowledge-Based Systems, 289: 111524. https://doi.org/10.1016/j.knosys.2024.111524.
Chatterjee, S., Dalton, J. 2025. QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking. Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval: 2255–2265. https://doi.org/10.1145/3726302.3730065.
Devlin J., Chang M.-W., Lee, K., Toutanova K. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1: 4171–4186. https://doi.org/10.18653/v1/N19-1423.
Kruhlov, V., Bobos, O., Hnylianska, O., Rossikhin, V., & Kolomiiets, Y. 2024. The Role of Using Artificial Intelligence for Improving the Public Service Provision and Fraud Prevention. Pakistan Journal of Criminology, 16(2): 913–928.
Kyurkchiev P, Iliev A, Kyurkchiev N. 2026. Semantic Search for System Dynamics Models Using Vector Embeddings in a Cloud Microservices Environment. Future Internet, 18(2): 86. https://doi.org/10.3390/fi18020086.
Pan Y., Wang L. 2024. Retrieval-Augmented Generation for Code Summarization via Hybrid GNN. IEEE Trans. Softw. Eng. 50:1234–1250.
Papageorgiou G, Sarlis V, Maragoudakis M, Tjortjis C. 2025. Hybrid Multi-Agent GraphRAG for E-Government: Towards a Trustworthy AI Assistant. Applied Sciences. 15(11): 6315. https://doi.org/10.3390/app15116315
Papageorgiou G, Sarlis V, Maragoudakis M, Tjortjis C. 2025. A Multimodal Framework Embedding Retrieval-Augmented Generation with MLLMs for Eurobarometer Data. AI. 6(3): 50. https://doi.org/10.3390/ai6030050
Raj M., Mishra, N. 2025. Exploring new Approaches for Information Retrieval through Natural Language Processing, arXiv e-prints, Art. no. arXiv:2505.02199, doi:10.48550/arXiv.2505.02199.
Sadykova T., Sinchev B., Young I.C., Auyezova А. 2025. The application of vector space models in intelligent information retrieval systems. Academic Scientific Journal of Computer Science, 355(3), 160–175. https://doi.org/10.32014/2025.2518-1726.370
Sarmah B., Hall B., Rao R., Patel S., Pasquali S., Mehta D. 2024. HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction. arXiv preprint arXiv:2408.04948. https://doi.org/10.48550/arXiv.2408.04948
Zhu X., Guo X., Cao S., Li S., Gong J. 2024. StructuGraphRAG: Structured document-informed knowledge graphs for retrieval-augmented generation. In Proceedings of the AAAI symposium series, 4(1): 242–251.
Abstract views: 0
Share
Published
How to Cite
Issue
Section
Copyright (c) 2026 Economics. Information Technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
