Link Prediction in Opportunistic Networks using Deep Neural Networks

• Vinícius S. Thiago IME
• Ronaldo M. Salles IME / Instituto Politécnico do Porto
• Julio Cesar Duarte IME
• Gabriela M. S. Dias IME

DOI: https://doi.org/10.5753/wtf.2024.2834

Abstract

Opportunistic Networks are mobile wireless networks without a fixed infrastructure that present unique challenges in the context of link prediction, a traditional problem in computer networks. Although several approaches have been proposed to solve this problem, the application of such techniques in opportunistic networks appears as a promising strategy to improve packet delivery. This paper carries out an in-depth analysis, comparing Machine Learning methods used in the task of link prediction in opportunistic networks. Solutions containing Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, and Attention Mechanisms are analyzed. The experiments use two datasets from real opportunistic networks, ITC and Infocom06. From the performance analysis, it was possible to observe that Convolutional Neural Networks using two-dimensional convolutions are promising options for link prediction, having obtained values of 0.9831 for AUC and 0.7590 for PRAUC in Infocom06 data.

References

Cai, X., Shu, J., and Al-Kali, M. (2018). Link prediction approach for opportunistic networks based on recurrent neural network. IEEE Access, 7:2017–2025.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.

Faceli, K., Lorena, A. C., Gama, J., Almeida, T. A. d., and Carvalho, A. C. P. d. L. F. d. (2021). Inteligência artificial: uma abordagem de aprendizado de máquina. LTC.

Fu, X., Yao, H., Postolache, O., and Yang, Y. (2019). Message forwarding for wsn-assisted opportunistic network in disaster scenarios. Journal of Network and Computer Applications, 137:11–24.

Galkin, M., Yuan, X., Mostafa, H., Tang, J., and Zhu, Z. (2023). Towards foundation models for knowledge graph reasoning. arXiv preprint arXiv:2310.04562.

Garg, P., Dixit, A., and Sethi, P. (2022). Ml-fresh: novel routing protocol in opportunistic networks using machine learning. Computer Systems Science & Engineering, Forthcoming.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.

Liao, Z., Liu, L., and Chen, Y. (2020). A novel link prediction method for opportunistic networks based on random walk and a deep belief network. Ieee Access, 8:16236–16247.

Ma, Y. and Shu, J. (2019). Opportunistic networks link prediction method based on bayesian recurrent neural network. IEEE access, 7:185786–185795.

Schubert, S., Neubert, P., Pöschmann, J., and Protzel, P. (2019). Circular convolutional neural networks for panoramic images and laser data. In 2019 IEEE intelligent vehicles symposium (IV), pages 653–660. IEEE.

Scott, J., Gass, R., Crowcroft, J., Hui, P., Diot, C., and Chaintreau, A. (2022). Crawdad cambridge/haggle (v. 2009-05-29). DOI: 10.15783/C70011. [Online, acesso em 24-agosto-2023].

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-c. (2015). Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28.

Shu, J., Li, J., and Zhang, X. (2022a). Link prediction based on 3d convolutional neural network. In 2022 IEEE/CIC International Conference on Communications in China (ICCC), pages 156–161. IEEE.

Shu, J., Shi, J., and Liao, L. (2022b). Link prediction model for opportunistic networks based on feature fusion. IEEE Access, 10:80900–80909.

Tan, C., Gao, Z., Li, S., and Li, S. Z. (2022). Simvp: Towards simple yet powerful spatiotemporal predictive learning. arXiv preprint arXiv:2211.12509.

Tan, C., Li, S., Gao, Z., Guan, W., Wang, Z., Liu, Z., Wu, L., and Li, S. Z. (2023). Openstl: A comprehensive benchmark of spatio-temporal predictive learning. In Conference on Neural Information Processing Systems Datasets and Benchmarks Track.

The PyTorch Foundation (2023). Pytorch. Disponível em [link]. [Online, acesso em 30-novembro-2023].

Wang, T.-H., Huang, H.-J., Lin, J.-T., Hu, C.-W., Zeng, K.-H., and Sun, M. (2018). Omni-directional cnn for visual place recognition and navigation. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 2341–2348. IEEE.

Yemeni, Z., Shu, J., Zhang, X., and Liu, L. (2019). A dbn approach to predict the link in opportunistic networks. In Recent Developments in Intelligent Computing, Communication and Devices: Proceedings of ICCD 2017, pages 575–587. Springer.