Utilizando aprendizado por representação para a classificação de laços sociais da IoT

  • Jamisson J. Júnior UFOP
  • Thiago S. Figueiredo UFOP
  • Ramon Lopes UFRB
  • Luiz C. B. Torres UFOP
  • Bruno P. Santos UFOP

Resumo


A Internet of Things (IoT) tem sido marcada pelas interações entre dispositivos que cooperam para realizar atividades. A partir deste ambiente cibernético e conectado, um possível paradigma derivado é o Social IoT (SIoT), onde múltiplos tipos de relacionamentos e confiabilidade podem ser estabelecidos entre dispositivos. Neste cenário, abordamos as questões de como modelar laços sociais em IoT e na proposição de modelos para, automaticamente, classificar e predizer relações em SIoT. Este artigo propõe a utilização de aprendizado por representação para classificar diferentes tipos de laços sociais em SIoT. Para isso, utiliza-se como estratégias para classificação Graph Neural Networks (GNN) ou Algoritmos Tradicionais de Classificação (ATC). Em nossos experimentos, GNN é rápido na etapa de treinamento e apresenta métricas F1-{macro, micro} de 0.61 e 0.88, respectivamente. Ao usar ATC, o treinamento é 121× até 11.235× mais lento que GNN, ao passo que as métricas F1-score alcançam 0.86 e 0.95, respetivamente.

Referências

Abdelrahman, M., Chong, A., and Miller, C. (2020). Build2vec: Building representation in vector space. arXiv preprint arXiv:2007.00740.

Aljubairy, A., Zhang, W. E., Sheng, Q. Z., and Alhazmi, A. (2020). Siotpredict: A framework for predicting relationships in the social internet of things. In Dustdar, S., Yu, E., Salinesi, C., Rieu, D., and Pant, V., editors, Advanced Information Systems Engineering, Cham. Springer International Publishing.

Atzori, L., Iera, A., and Morabito, G. (2014). From "smart objects"to "social objects": The next evolutionary step of the internet of things. IEEE Communications Magazine.

Atzori, L., Iera, A., Morabito, G., and Nitti, M. (2012a). The social internet of things (siot) - when social networks meet the internet of things: Concept, architecture and network characterization. Computer Networks.

Atzori, L., Iera, A., Morabito, G., and Nitti, M. (2012b). The social internet of things (siot)-when social networks meet the internet of things: Concept, architecture and network characterization. Computer networks.

Barker, S. and Rothmuller, M. (2020). The internet of things: Consumer, industrial & public services 2020-2024.

Bellman, R. (1956). Dynamic programming and lagrange multipliers. Proceedings of the National Academy of Sciences of the United States of America, 42(10):767.

Corso, G., Cavalleri, L., Beaini, D., Lió€, P., and VelicÌŒkovicÌ, P. (2020). Principal neighbourhood aggregation for graph nets. arXiv preprint arXiv:2004.05718.

Glasmachers, T. (2017). Limits of end-to-end learning. Proceedings of Machine Learning Research.

Grover, A. and Leskovec, J. (2016). node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining.

Gupta, C., Jain, Y., De, A., and Chakrabarti, S. (2021). Integrating transductive and inductive embeddings improves link prediction accuracy. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management.

Hamilton, W. L., Ying, R., and Leskovec, J. (2017). Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems.

Hu, L., Wu, G., Xing, Y., and Wang, F. (2019). Things2Vec: Semantic modeling in the Internet of Things with graph representation learning. IEEE Internet of Things Journal.

Júnior, J. J., Figueiredo, T. S., Torres, L. C., and Santos, B. P. (2021). Como os objetos da Internet das Coisas se comportam? Uma análise através de métricas quantitativas. In Anais do V Workshop de Computação Urbana. SBC.

Khanfor, A., Ghazzai, H., Yang, Y., and Massoud, Y. (2019). Application of community detection algorithms on social internet-of-things networks. In 2019 31st International Conference on Microelectronics (ICM).

Khanfor, A., Nammouchi, A., Ghazzai, H., Yang, Y., Haider, M. R., and Massoud, Y. (2020). Graph neural networks-based clustering for social internet of things. In 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS). IEEE.

Marche, C., Atzori, L., and Nitti, M. (2018). A dataset for performance analysis of the social internet of things. In 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

Marche, C., Atzori, L., Pilloni, V., and Nitti, M. (2020). How to exploit the social internet of things: Query generation model and device profiles' dataset. Computer Networks.

Marche, C. and Nitti, M. (2020). Trust-related Attacks and their Detection: a Trust Management Model for the Social IoT. IEEE Transactions on Network and Service Management.

Morris, C., Ritzert, M., Fey, M., Hamilton, W. L., Lenssen, J. E., Rattan, G., and Grohe, M. (2019). Weisfeiler and leman go neural: Higher-order graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence.

Nitti, M., Atzori, L., and Cvijikj, I. P. (2014). Network navigability in the social internet of things. In 2014 IEEE world forum on internet of things (WF-IoT). IEEE.

Oliveau, Q. and Sahbi, H. (2018). From transductive to inductive semi-supervised attributes for ship category recognition. In IGARSS 2018 2018 IEEE International Geoscience and Remote Sensing Symposium.

Perozzi, B., Al-Rfou, R., and Skiena, S. (2014). Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA. Association for Computing Machinery.

Sanchez-Lengeling, B., Reif, E., Pearce, A., and Wiltschko, A. B. (2021). A Gentle Introduction to Graph Neural Networks. Distill. https://distill.pub/2021/gnn-intro.

Santos, B. P., Goussevskaia, O., Vieira, L. F., Vieira, M. A., and Loureiro, A. A. (2018). Mobile matrix: routing under mobility in IoT, IoMT, and social IoT. Ad Hoc Networks.

Santos, B. P., Silva, L. A., Celes, C. S., Borges Neto, J. B., Peres, B. S., Vieira, M. A. M., Vieira, L. F. M., Goussevskaia, O. N., and Loureiro, A. A. (2016). Internet das coisas: da teoria à prática. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos.

Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., and Monfardini, G. (2008). The graph neural network model. IEEE transactions on neural networks.

Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015). Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web.

Wei, D., Ning, H., Qian, Y., and Zhu, T. (2018). Social relationship for physical objects. International Journal of Distributed Sensor Networks.

Xing, Y., Hu, L., Zhang, X., Wu, G., and Wang, F. (2021). Nonnegative Matrix Factorization Based Heterogeneous Graph Embedding Method for Trigger-Action Programming in IoT. IEEE Transactions on Industrial Informatics.

Xu, D., Cheng, W., Luo, D., Liu, X., and Zhang, X. (2019). Spatio-temporal attentive rnn for node classification in temporal attributed graphs. In IJCAI-19.

Zhou, J., Cui, G., Zhang, Z., Yang, C., Liu, Z., and Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open.
Publicado
23/05/2022
J. JÚNIOR, Jamisson; FIGUEIREDO, Thiago S.; LOPES, Ramon; TORRES, Luiz C. B.; SANTOS, Bruno P.. Utilizando aprendizado por representação para a classificação de laços sociais da IoT. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 6. , 2022, Fortaleza. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 112-125. ISSN 2595-2706. DOI: https://doi.org/10.5753/courb.2022.223493.