Diversidade na Construção de Vizinhanças para Redes Convolucionais de Grafos em Classificação de Imagens
Resumo
O crescente volume de imagens disponíveis exige métodos eficazes de classificação. Muitos modelos de aprendizado profundo dependem de grandes conjuntos de dados rotulados, cuja obtenção é custosa. O aprendizado semi-supervisionado surge como alternativa promissora, e as redes convolucionais de grafos (GCNs) exploram relações entre amostras rotuladas e não rotuladas. Contudo, a abordagem comum para imagens emprega grafos baseados apenas em similaridade, o que pode restringir a variedade das vizinhanças. Este mestrado investiga a construção de grafos com diversidade para GCNs, sob a hipótese de que vizinhanças mais diversas favorecem o aprendizado. Propõe-se o método BRID-G, que apresenta resultados preliminares promissores.
Palavras-chave:
Redes Convolucionais de Grafos, Classificação de Imagens, Diversidade
Referências
Alon, U. and Yahav, E. (2021). On the bottleneck of graph neural networks and its practical implications. In International Conference on Learning Representations (ICLR).
Awais, M., Naseer, M., Khan, S., Anwer, R. M., Cholakkal, H., Shah, M., Yang, M.-H., and Khan, F. S. (2025). Foundation models defining a new era in vision: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2245–2264.
Carbonell, J. G. and Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 335–336. ACM.
Figuerêdo, J. S. L., Maia, A. L. M., and Calumby, R. T. (2025). GDRF: An innovative graph-based rank fusion method for enhancing diversity in image metasearch. Journal of Information and Data Management, 16(1):21–27.
Gao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X., and Li, Y. (2023). A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems, 1(1).
Gasteiger, J., Bojchevski, A., and Günnemann, S. (2019). Predict then propagate: Graph neural networks meet personalized pagerank. In International Conference on Learning Representations (ICLR).
Kipf, T. N. and Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR).
Liu, G.-H. and Yang, J.-Y. (2013). Content-based image retrieval using color difference histogram. Pattern Recognition, 46(1):188 – 198.
Nilsback, M.-E. and Zisserman, A. (2006). A visual vocabulary for flower classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1447–1454.
Oono, K. and Suzuki, T. (2020). Graph neural networks exponentially lose expressive power for node classification. In International Conference on Learning Representations (ICLR).
Parkhi, O. M., Vedaldi, A., Zisserman, A., and Jawahar, C. V. (2012). Cats and dogs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3498–3505.
Santos, L. F. D., Oliveira, W. D., Ferreira, M. R. P., Traina, A. J. M., and Traina, C. (2013). Parameter-free and domain-independent similarity search with diversity. In Proceedings of the 25th International Conference on Scientific and Statistical Database Management, SSDBM ’13, New York, NY, USA. Association for Computing Machinery.
Valem, L. P., Pedronette, D. C. G., and Latecki, L. J. (2023). Graph convolutional networks based on manifold learning for semi-supervised image classification. Computer Vision and Image Understanding, 227:103618.
Webber, W., Moffat, A., and Zobel, J. (2010). A similarity measure for indefinite rankings. ACM Transactions on Information Systems, 28(4):20:1–20:38.
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019). Simplifying graph convolutional networks. In International Conference on Machine Learning (ICML).
Xu, J., Chen, G., Lu, J., and Lin, Y. (2025). Graph neural networks with diversity-aware neighbor selection and dynamic multi-scale fusion for multivariate time series forecasting. arXiv preprint arXiv:2509.23671.
Awais, M., Naseer, M., Khan, S., Anwer, R. M., Cholakkal, H., Shah, M., Yang, M.-H., and Khan, F. S. (2025). Foundation models defining a new era in vision: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2245–2264.
Carbonell, J. G. and Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. In Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 335–336. ACM.
Figuerêdo, J. S. L., Maia, A. L. M., and Calumby, R. T. (2025). GDRF: An innovative graph-based rank fusion method for enhancing diversity in image metasearch. Journal of Information and Data Management, 16(1):21–27.
Gao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X., and Li, Y. (2023). A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems, 1(1).
Gasteiger, J., Bojchevski, A., and Günnemann, S. (2019). Predict then propagate: Graph neural networks meet personalized pagerank. In International Conference on Learning Representations (ICLR).
Kipf, T. N. and Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR).
Liu, G.-H. and Yang, J.-Y. (2013). Content-based image retrieval using color difference histogram. Pattern Recognition, 46(1):188 – 198.
Nilsback, M.-E. and Zisserman, A. (2006). A visual vocabulary for flower classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1447–1454.
Oono, K. and Suzuki, T. (2020). Graph neural networks exponentially lose expressive power for node classification. In International Conference on Learning Representations (ICLR).
Parkhi, O. M., Vedaldi, A., Zisserman, A., and Jawahar, C. V. (2012). Cats and dogs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3498–3505.
Santos, L. F. D., Oliveira, W. D., Ferreira, M. R. P., Traina, A. J. M., and Traina, C. (2013). Parameter-free and domain-independent similarity search with diversity. In Proceedings of the 25th International Conference on Scientific and Statistical Database Management, SSDBM ’13, New York, NY, USA. Association for Computing Machinery.
Valem, L. P., Pedronette, D. C. G., and Latecki, L. J. (2023). Graph convolutional networks based on manifold learning for semi-supervised image classification. Computer Vision and Image Understanding, 227:103618.
Webber, W., Moffat, A., and Zobel, J. (2010). A similarity measure for indefinite rankings. ACM Transactions on Information Systems, 28(4):20:1–20:38.
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019). Simplifying graph convolutional networks. In International Conference on Machine Learning (ICML).
Xu, J., Chen, G., Lu, J., and Lin, Y. (2025). Graph neural networks with diversity-aware neighbor selection and dynamic multi-scale fusion for multivariate time series forecasting. arXiv preprint arXiv:2509.23671.
Publicado
08/09/2026
Como Citar
DE PAULO, Diego Giaretta; PASCOTTI VALEM, Lucas.
Diversidade na Construção de Vizinhanças para Redes Convolucionais de Grafos em Classificação de Imagens. In: WORKSHOP DE TESES E DISSERTAÇÕES (WTDBD) - SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 307-313.
DOI: https://doi.org/10.5753/sbbd_estendido.2026.249487.
