Usando Representações Não Supervisionadas Para Extração de Características Em Grafos em Dados de Redes Sociais
Resumo
Embora Redes Neurais em Grafos (Graph Neural Networks - GNNs) sejam essenciais para redes sociais, a alta sobrecarga computacional e o intenso ajuste de parâmetros frequentemente dificultam sua adoção. Propomos um framework de aprendizado desacoplado para classificação de nós, substituindo arquiteturas profundas por embeddings estruturais de baixa dimensionalidade combinados com aprendizado de máquina tradicional. Ao separar as fases de representação e classificação, nosso método reduz significativamente o uso de memória e o tempo de treinamento. Resultados em diversos datasets demonstram desempenho competitivo, oferecendo uma alternativa escalável e interpretável às GNNs convencionais.
Referências
Bengio, Y., Courville, A., and Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8):1798–1828.
Brito, M. L. L., Ferreira, M. C. M., Portela, A. L. C., and Gomes, R. L. (2026). Ai-based estimation of bandwidth availability for data offloading in edge-cloud computing. IEEE Networking Letters, 8:69–73.
Brochier, R., Guille, A., and Velcin, J. (2019). Global vectors for node representations. In The World Wide Web Conference, pages 2587–2593.
Cai, H., Zheng, V. W., and Chang, K. C.-C. (2018). A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE transactions on knowledge and data engineering, 30(9):1616–1637.
da Silva, M. d. V. D., Rocha, A., Gomes, R. L., and Nogueira, M. (2021). Lightweight data compression for low energy consumption in industrial internet of things. In 2021 IEEE 18th Annual Consumer Communications Networking Conference (CCNC), pages 1–2.
Dalvi, A. and Honavar, V. (2025). Hyperdimensional representation learning for node classification and link prediction. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pages 88–97.
Epasto, A. and Perozzi, B. (2019). Is a single embedding enough? learning node representations that capture multiple social contexts. In The world wide web conference, pages 394–404.
Ferreira, M. C., Ribeiro, S. E., Nobre, F. V., Linhares, M. L., Araújo, T. P., and Gomes, R. L. (2024). Mitigating measurement failures in throughput performance forecasting. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–7.
Fortunato, S. (2010). Community detection in graphs. Physics reports, 486(3-5):75–174.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. [link].
Goyal, P., Kamra, N., He, X., and Liu, Y. (2018). Dyngem: Deep embedding method for dynamic graphs. arXiv preprint arXiv:1805.11273.
Heidari, F. and Papagelis, M. (2020). Evolving network representation learning based on random walks. Applied network science, 5(1):18.
Khan, I., Bokhari, M. U., Afzal, S., and Alam, S. (2025). Distance driven graph neural network for advanced node classification through feature augmentation. Discover Computing, 28(1):70.
Khoshraftar, S. and An, A. (2024). A survey on graph representation learning methods. ACM Transactions on Intelligent Systems and Technology, 15(1):1–55.
Lecca, P. and Lecca, M. (2023). Graph embedding and geometric deep learning relevance to network biology and structural chemistry. Frontiers in Artificial Intelligence, 6:1256352.
Li, S., Zaidi, N. A., Du, M., Zhou, Z., Zhang, H., and Li, G. (2024). Property graph representation learning for node classification. Knowledge and Information Systems, 66(1):237–265.
Luo, Y., Liu, Q., Shi, L., and Wu, X.-M. (2024). Structure-aware semantic node identifiers for learning on graphs. arXiv e-prints, pages arXiv–2405.
Mahdavi, S., Khoshraftar, S., and An, A. (2019). Dynamic joint variational graph autoencoders. In Joint European conference on machine learning and knowledge discovery in databases, pages 385–401. Springer.
Makarov, I., Kiselev, D., Nikitinsky, N., and Subelj, L. (2021). Survey on graph embeddings and their applications to machine learning problems on graphs. PeerJ Computer Science, 7:e357.
Nobre, F. V. J., Silva, D. d. S., Ferreira, M. C. M. M., Brito, M. L. M. L., de Araújo, T. P., and Gomes, R. L. (2025). Time-weighted correlation approach to identify high delay links in internet service providers. Journal of Internet Services and Applications, 16(1):419–430.
Pimenta, I., Silva, D., Moura, E., Silveira, M., and Gomes, R. L. (2024a). Impact of data anonymization in machine learning models. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, pages 188–191.
Pimenta, I. A., Aquino, C. A., Almeida, Y. O., Lima, V. C., and Gomes, R. L. (2024b). Prediction of multimedia quality over 5g networks in urban environments. In 2024 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pages 748–755.
Pimenta, I. A., Lee, M. H., Bittencourt, L. F., and Gomes, R. L. (2025). Adaptive privacy based on mutual information for machine learning in edge-cloud environments. IEEE Networking Letters.
Rozemberczki, B., Allen, C., and Sarkar, R. (2019). Multi-scale attributed node embedding.
Souza, M. S., Ribeiro, S. E. S. B., Lima, V. C., Cardoso, F. J., and Gomes, R. L. (2024). Combining regular expressions and machine learning for sql injection detection in urban computing. Journal of Internet Services and Applications, 15(1):103–111.
Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., and Yang, S. (2017). Community preserving network embedding. In Proceedings of the AAAI conference on artificial intelligence, volume 31.
Wei, X., Xu, L., Cao, B., and Yu, P. S. (2017). Cross view link prediction by learning noise-resilient representation consensus. In Proceedings of the 26th international conference on World Wide Web, pages 1611–1619.
Xiao, W., Zhao, H., Zheng, V. W., and Song, Y. (2020). Vertex-reinforced random walk for network embedding. In Proceedings of the 2020 SIAM International Conference on Data Mining, pages 595–603. SIAM.
Zhu, H. and Koniusz, P. (2021). Refine: Random range finder for network embedding. In Proceedings of the 30th ACM international conference on information & knowledge management, pages 3682–3686.
Brito, M. L. L., Ferreira, M. C. M., Portela, A. L. C., and Gomes, R. L. (2026). Ai-based estimation of bandwidth availability for data offloading in edge-cloud computing. IEEE Networking Letters, 8:69–73.
Brochier, R., Guille, A., and Velcin, J. (2019). Global vectors for node representations. In The World Wide Web Conference, pages 2587–2593.
Cai, H., Zheng, V. W., and Chang, K. C.-C. (2018). A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE transactions on knowledge and data engineering, 30(9):1616–1637.
da Silva, M. d. V. D., Rocha, A., Gomes, R. L., and Nogueira, M. (2021). Lightweight data compression for low energy consumption in industrial internet of things. In 2021 IEEE 18th Annual Consumer Communications Networking Conference (CCNC), pages 1–2.
Dalvi, A. and Honavar, V. (2025). Hyperdimensional representation learning for node classification and link prediction. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pages 88–97.
Epasto, A. and Perozzi, B. (2019). Is a single embedding enough? learning node representations that capture multiple social contexts. In The world wide web conference, pages 394–404.
Ferreira, M. C., Ribeiro, S. E., Nobre, F. V., Linhares, M. L., Araújo, T. P., and Gomes, R. L. (2024). Mitigating measurement failures in throughput performance forecasting. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–7.
Fortunato, S. (2010). Community detection in graphs. Physics reports, 486(3-5):75–174.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. [link].
Goyal, P., Kamra, N., He, X., and Liu, Y. (2018). Dyngem: Deep embedding method for dynamic graphs. arXiv preprint arXiv:1805.11273.
Heidari, F. and Papagelis, M. (2020). Evolving network representation learning based on random walks. Applied network science, 5(1):18.
Khan, I., Bokhari, M. U., Afzal, S., and Alam, S. (2025). Distance driven graph neural network for advanced node classification through feature augmentation. Discover Computing, 28(1):70.
Khoshraftar, S. and An, A. (2024). A survey on graph representation learning methods. ACM Transactions on Intelligent Systems and Technology, 15(1):1–55.
Lecca, P. and Lecca, M. (2023). Graph embedding and geometric deep learning relevance to network biology and structural chemistry. Frontiers in Artificial Intelligence, 6:1256352.
Li, S., Zaidi, N. A., Du, M., Zhou, Z., Zhang, H., and Li, G. (2024). Property graph representation learning for node classification. Knowledge and Information Systems, 66(1):237–265.
Luo, Y., Liu, Q., Shi, L., and Wu, X.-M. (2024). Structure-aware semantic node identifiers for learning on graphs. arXiv e-prints, pages arXiv–2405.
Mahdavi, S., Khoshraftar, S., and An, A. (2019). Dynamic joint variational graph autoencoders. In Joint European conference on machine learning and knowledge discovery in databases, pages 385–401. Springer.
Makarov, I., Kiselev, D., Nikitinsky, N., and Subelj, L. (2021). Survey on graph embeddings and their applications to machine learning problems on graphs. PeerJ Computer Science, 7:e357.
Nobre, F. V. J., Silva, D. d. S., Ferreira, M. C. M. M., Brito, M. L. M. L., de Araújo, T. P., and Gomes, R. L. (2025). Time-weighted correlation approach to identify high delay links in internet service providers. Journal of Internet Services and Applications, 16(1):419–430.
Pimenta, I., Silva, D., Moura, E., Silveira, M., and Gomes, R. L. (2024a). Impact of data anonymization in machine learning models. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, pages 188–191.
Pimenta, I. A., Aquino, C. A., Almeida, Y. O., Lima, V. C., and Gomes, R. L. (2024b). Prediction of multimedia quality over 5g networks in urban environments. In 2024 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pages 748–755.
Pimenta, I. A., Lee, M. H., Bittencourt, L. F., and Gomes, R. L. (2025). Adaptive privacy based on mutual information for machine learning in edge-cloud environments. IEEE Networking Letters.
Rozemberczki, B., Allen, C., and Sarkar, R. (2019). Multi-scale attributed node embedding.
Souza, M. S., Ribeiro, S. E. S. B., Lima, V. C., Cardoso, F. J., and Gomes, R. L. (2024). Combining regular expressions and machine learning for sql injection detection in urban computing. Journal of Internet Services and Applications, 15(1):103–111.
Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., and Yang, S. (2017). Community preserving network embedding. In Proceedings of the AAAI conference on artificial intelligence, volume 31.
Wei, X., Xu, L., Cao, B., and Yu, P. S. (2017). Cross view link prediction by learning noise-resilient representation consensus. In Proceedings of the 26th international conference on World Wide Web, pages 1611–1619.
Xiao, W., Zhao, H., Zheng, V. W., and Song, Y. (2020). Vertex-reinforced random walk for network embedding. In Proceedings of the 2020 SIAM International Conference on Data Mining, pages 595–603. SIAM.
Zhu, H. and Koniusz, P. (2021). Refine: Random range finder for network embedding. In Proceedings of the 30th ACM international conference on information & knowledge management, pages 3682–3686.
Publicado
25/05/2026
Como Citar
NASCIMENTO, Erick S.; PIMENTA, Ivo A.; LEE, Marcelo H.; SANTOS, Janaína R.; ARAÚJO, Thelmo P.; GOMES, Rafael L..
Usando Representações Não Supervisionadas Para Extração de Características Em Grafos em Dados de Redes Sociais. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 44. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1499-1512.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2026.19314.
