Consulta Eficiente aos K-Vizinhos mais Próximos com Seleção Inteligente de Nó em Árvores Métricas
Resumo
A consulta K-Vizinhos Mais Próximos (KNN) é um método amplamente usado em mineração e aprendizado de máquina. Para viabilizar a sua aplicação em volumes de dados que excedem a memória RAM, utilizam-se estruturas de acesso métricas que reduzem seu custo computacional. Esta proposta introduz o algoritmo KNN Neural que altera o algoritmo clássico utilizando uma rede neural para inferir o nó inicial e determinar o valor do raio de corte. Os experimentos mostram uma redução média de até 60% no tempo de execução em relação ao KNN clássico.
Palavras-chave:
k-NN, Consulta, Árvores Métricas, Seleção Inteligente
Referências
Benrazek, A.; Kemouguette, I.; Kouahla, Z.; Farou, B.; Seridi, H. (2026). Optimizing Overlap in Tree-Based Indexing Structures for Enhanced K-NN Search Efficiency. Journal of Eng.and Technology for Industrial Applications. DOI: 10.5935/jetia.v12i57.2744.
Ciaccia, P., Patella, M., and Zezula, P. (1997). M-tree: An Efficient Access Method for Similarity Search in Metric Spaces. In Proc. Int. Conf. VLDB, pages 426–435, USA.
Daulay, R. S. A.; Efendi, S.; Suherman (2023). Review of literature on improving the KNN algorithm. Transactions on Engineering and Computing Sciences, [S. l.], v. 11, n. 3, p. 63–72, 2023. DOI: 10.14738/tecs.113.14768.
Eclipse Foundation (2026). Deeplearning4j: Open-source, distributed deep learning for the JVM. Disponível: [link]. Acesso: mai/2026.
Gou, J.; Du, L.; Zhang, Y.; Xiong, T. (2012). A New Distance-weighted k-nearest Neighbor Classifier. Journal of Information and Computational Science. 1429-1436.
Hjaltason, G. R.; Samet, H. (2003). Index-driven similarity search in metric spaces. ACM Transactions on Database Systems, 28(4), 517-580. DOI: 10.1145/958942.958948.
Halder, R.K.; Uddin, M.N.; Uddin, M.A.; Aryal S.; Khraisat, A.(2024) Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data 11, 113 (2024). DOI: 10.1186/s40537-024-00973-y.
Carvalho, L. O., Seraphim, T. F. P., Traina, C., and Seraphim, E. (2013). Obinject: a noodmg persistence and indexing framework for object injection. J. Inf. Data Manag., 4:220–235.
Procházka, D.; Slanináková, T.; Čerňanský, J.; Olha, J.; Antol, M.; Dohnal, V. (2025). Scaling Learned Metric Index to 100M Datasets. Similarity Search and Applications. SISAP 2024. Lecture Notes in Computer Science, vol 15268. Springer.
Schubert, E.; Zimek A. (2010). ELKI Multi-View Clustering Data Sets Based on the Amsterdam Library of Object Images. Zenodo, 2010, DOI: 10.5281/zenodo.6355684
Tian, Y.; Yan, T.; Zhao, X.; Huang, K.; Zhou, X. (2022). A Learned Index for Exact Similarity Search in Metric Spaces. IEEE Transactions on Knowledge and Data Engineering (TKDE). DOI: 10.1109/TKDE.2022.3206441
Traina Jr.; C., Traina, A. J. M.; Faloutsos, C.; Seeger, B. (2002). Fast Indexing and Visualization of Metric Data Sets using Slim-Trees. IEEE Transactions on Knowledge and Data Engineering (TKDE). 14(2). DOI: 10.1109/69.991715
Silva, W. Z.; Traina A. J. M.; Traina Jr., C. (2026), Include-Slim: Supporting Similarity Retrieval Variants with a Metric Access Method in IEEE Open Journal of the Computer Society, pp. 1-13, PrePrints 5555. DOI: 10.1109/OJCS.2026.3687006.
Wu, X.; Kumar, V.; Quinlan, J. R.; Ghosh, J.; Yang, Q.; Motoda, H.; Mclachlan, G. J.; Ng, A.; Liu, B.; Yu, P. S. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, [S. l.], v. 14, n. 1, p. 1–37, 2008. DOI: 10.1007/s10115-007-0114-2.
Wang, Y.; Wang B.; Zhu R.; Sun W.; Yang X.; (2026). LM-Tree: A Hybrid Learned Index for Similarity Search in Metric Spaces. Proc. ACM Manag. Data 4, 1, Article 51 (2026), 25 pages. DOI: 10.1145/3786665.
Ciaccia, P., Patella, M., and Zezula, P. (1997). M-tree: An Efficient Access Method for Similarity Search in Metric Spaces. In Proc. Int. Conf. VLDB, pages 426–435, USA.
Daulay, R. S. A.; Efendi, S.; Suherman (2023). Review of literature on improving the KNN algorithm. Transactions on Engineering and Computing Sciences, [S. l.], v. 11, n. 3, p. 63–72, 2023. DOI: 10.14738/tecs.113.14768.
Eclipse Foundation (2026). Deeplearning4j: Open-source, distributed deep learning for the JVM. Disponível: [link]. Acesso: mai/2026.
Gou, J.; Du, L.; Zhang, Y.; Xiong, T. (2012). A New Distance-weighted k-nearest Neighbor Classifier. Journal of Information and Computational Science. 1429-1436.
Hjaltason, G. R.; Samet, H. (2003). Index-driven similarity search in metric spaces. ACM Transactions on Database Systems, 28(4), 517-580. DOI: 10.1145/958942.958948.
Halder, R.K.; Uddin, M.N.; Uddin, M.A.; Aryal S.; Khraisat, A.(2024) Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data 11, 113 (2024). DOI: 10.1186/s40537-024-00973-y.
Carvalho, L. O., Seraphim, T. F. P., Traina, C., and Seraphim, E. (2013). Obinject: a noodmg persistence and indexing framework for object injection. J. Inf. Data Manag., 4:220–235.
Procházka, D.; Slanináková, T.; Čerňanský, J.; Olha, J.; Antol, M.; Dohnal, V. (2025). Scaling Learned Metric Index to 100M Datasets. Similarity Search and Applications. SISAP 2024. Lecture Notes in Computer Science, vol 15268. Springer.
Schubert, E.; Zimek A. (2010). ELKI Multi-View Clustering Data Sets Based on the Amsterdam Library of Object Images. Zenodo, 2010, DOI: 10.5281/zenodo.6355684
Tian, Y.; Yan, T.; Zhao, X.; Huang, K.; Zhou, X. (2022). A Learned Index for Exact Similarity Search in Metric Spaces. IEEE Transactions on Knowledge and Data Engineering (TKDE). DOI: 10.1109/TKDE.2022.3206441
Traina Jr.; C., Traina, A. J. M.; Faloutsos, C.; Seeger, B. (2002). Fast Indexing and Visualization of Metric Data Sets using Slim-Trees. IEEE Transactions on Knowledge and Data Engineering (TKDE). 14(2). DOI: 10.1109/69.991715
Silva, W. Z.; Traina A. J. M.; Traina Jr., C. (2026), Include-Slim: Supporting Similarity Retrieval Variants with a Metric Access Method in IEEE Open Journal of the Computer Society, pp. 1-13, PrePrints 5555. DOI: 10.1109/OJCS.2026.3687006.
Wu, X.; Kumar, V.; Quinlan, J. R.; Ghosh, J.; Yang, Q.; Motoda, H.; Mclachlan, G. J.; Ng, A.; Liu, B.; Yu, P. S. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, [S. l.], v. 14, n. 1, p. 1–37, 2008. DOI: 10.1007/s10115-007-0114-2.
Wang, Y.; Wang B.; Zhu R.; Sun W.; Yang X.; (2026). LM-Tree: A Hybrid Learned Index for Similarity Search in Metric Spaces. Proc. ACM Manag. Data 4, 1, Article 51 (2026), 25 pages. DOI: 10.1145/3786665.
Publicado
08/09/2026
Como Citar
SERAPHIM, Enzo; PEDRAS, Luis Filipe L. J.; SERAPHIM, Thatyana F. P.; SANTOS, Lucio F. D.; CARVALHO, Luiz Olmes.
Consulta Eficiente aos K-Vizinhos mais Próximos com Seleção Inteligente de Nó em Árvores Métricas. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 959-965.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2026.249635.
