MUET logo

A Few-Shot Learning Framework for Understanding Mobile User Behavior

Authors

  • Shabana Hajano

    Department of Computer System Engineering, Mehran University of Engineering and Technology Jamshoro
    Author

  • Sanam Narejo

    Department of Computer System Engineering, Mehran University of Engineering and Technology Jamshoro
    Author

  • Sofia Hajano

    Department of Computer System Engineering, Mehran University of Engineering and Technology Jamshoro
    Author

  • Fouzia Hajano

    Department of Electronic Engineering, Mehran University of Engineering and Technology Jamshoro
    Author

DOI:

https://doi.org/10.22581/muet1982.0155

Keywords:

Few-Shot Learning, Meta-learning, Mobile data features, App usage prediction

Abstract

It is vital to understand the behavior of mobile users to provide them with personalized experiences, but obtaining large amounts of labelled data is difficult and expensive. In this paper, we explore using few-shot learning to overcome this challenge by allowing models to learn from only a few labelled examples. We focus on the classification of mobile users on behavior data, such as app usage, screen time, battery drain, and data usage. Using a meta-learning approach, our model is trained over 50 epochs with continuous monitoring of loss and accuracy. The results are promising; it shows a test accuracy of 98.75% and a loss reduction that shows that few shot learning can be an effective solution even when data is limited. This approach opens up new possibilities for analyzing mobile user behavior without requiring large amounts of labelled data, making it more practical for real-world applications.

Downloads

Author Biographies

  • Sanam Narejo, Department of Computer System Engineering, Mehran University of Engineering and Technology Jamshoro

    Associate Professor at Mehran UET , Jamshoro

  • Sofia Hajano, Department of Computer System Engineering, Mehran University of Engineering and Technology Jamshoro

    Lecturer at DUET , Karachi

  • Fouzia Hajano, Department of Electronic Engineering, Mehran University of Engineering and Technology Jamshoro

    Lecturer at University of Sindh, Jamshoro

References

[1] Vinyals, O., Blundell, C., Lillicrap, T., et al., "Matching networks for one-shot learning," in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2016, pp. 3630-3638.

[2] Snell, J., Swersky, K., & Zemel, R. S., "Prototypical networks for few-shot learning," in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4077-4087.

[3] Sung, F., Yang, Y., Zhang, L., et al., "Learning to compare: Relation networks for few-shot learning," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 1199-1208.

[4] Ravi, S., & Larochelle, H., "Optimization as a model for few-shot learning," in Proc. International Conference on Learning Representations (ICLR), 2017.

[5] Koch, G., Zemel, R., & Salakhutdinov, R., "Siamese neural networks for one-shot image recognition," in Proc. International Conference on Machine Learning (ICML), 2015.

[6] Pan, S. J., & Yang, Q., "A survey on transfer learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010.

[7] Finn, C., Abbeel, P., & Levine, S., "Model-agnostic meta-learning for fast adaptation of deep networks," in Proc. International Conference on Machine Learning (ICML), 2017, pp. 1126-1135.

[8] Zhang, H., Li, Y., & Choi, J., "Applying few-shot learning for predicting user behavior in social media platforms," IEEE Access, vol. 8, pp. 179462-179470, 2020.

[9] M. Gidaris and N. Komodakis, "Dynamic FewShot Visual Learning Without Forgetting," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 43674375. DOI: 10.1109/CVPR.2018.00459.

[10] S. Snell, K. Swersky, and R. Zemel, "Prototypical Networks for Few-shot Learning," in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.

[11] K. Sung et al., "Learning to Compare: Relation Network for Few-Shot Learning," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 1199-1208. DOI: 10.1109/CVPR.2018.00131.

[12] J. Triantafillou et al., "Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 7251-7260. DOI: 10.1109/CVPR42600.2020.00728.

[13] J. Sung et al., "A Metric Learning Approach to Few-Shot Learning," in Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, 2018, pp. 514-522. DOI: 10.1109/WACV.2018.00063.

[14] J. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra, "Matching Networks for One-Shot Learning," in Advances in Neural Information Processing Systems (NeurIPS), vol. 29, 2016.

[15] Y. Yue, H. Xu, and L. Yang, "From Sample Poverty to Rich Feature Learning: A New Metric Learning Method for Few-Shot Classification," IEEE

[16] Transactions on Neural Networks and Learning Systems, 2023. DOI: 10.1109/TNNLS.2023.1234567

[17] J. Kang and M. Chang, "Enhancing Few-Shot Image Classification With a Multi-Faceted SelfSupervised and Contrastive Learning Approach," IEEE Transactions on Image Processing, 2024. DOI: 10.1109/TIP.2024.10746489

[18] Koch, G., Zemel, R., & Salakhutdinov, R. (2015). Siamese neural networks for one-shot image recognition. International Conference on Machine Learning (ICML) Deep Learning Workshop.

[19] Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., & Wierstra, D. (2016). Matching networks for one-shot

Published

2025-10-28

Issue

Vol. 44 No. 4 (2025): October Issue

Section

Articles

License

Copyright (c) 2025 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

A Few-Shot Learning Framework for Understanding Mobile User Behavior. (2025). Mehran University Research Journal of Engineering and Technology, 44(4), 25-31. https://doi.org/10.22581/muet1982.0155

Similar Articles

31-40 of 67

You may also start an advanced similarity search for this article.