Evaluation of Semi-Supervised Learning Techniques for Improving Model Generalization in Sparse Data Environments
Keywords:
Semi-supervised learning, Sparse data, Model generalization, Consistency regularization, Pseudo-labelingAbstract
Sparse data environments challenge traditional machine learning models by limiting the availability of labeled examples. Semi-supervised learning (SSL) offers a promising direction by leveraging both labeled and unlabeled data to improve model generalization. This paper critically evaluates major SSL techniques, comparing their efficacy through empirical analysis and literature synthesis. This study explores consistency regularization, pseudo-labeling, and graph-based methods, examining their theoretical basis and practical impact under sparse conditions. Our results show that appropriate SSL strategies significantly boost performance even in data-scarce settings, thereby offering vital tools for real-world applications with annotation constraints.
References
Miyato, T., Maeda, S., Koyama, M., & Ishii, S. (2018). Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8), 1979–1993.
Balasubramanian, A., & Gurushankar, N. (2020). Hardware-Enabled AI for Predictive Analytics in the Pharmaceutical Industry. International Journal of Leading Research Publication (IJLRP), 1(4), 1–13.
Laine, S., & Aila, T. (2017). Temporal ensembling for semi-supervised learning. In Proceedings of the International Conference on Learning Representations (ICLR).
Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR).
Balasubramanian, A., & Gurushankar, N. (2020). AI-Driven Supply Chain Risk Management: Integrating Hardware and Software for Real-Time Prediction in Critical Industries. International Journal of Innovative Research in Engineering & Multidisciplinary Physical Sciences, 8(3), 1–11.
Oliver, A., Odena, A., Raffel, C., Cubuk, E. D., & Goodfellow, I. (2018). Realistic evaluation of deep semi-supervised learning algorithms. In Advances in Neural Information Processing Systems (NeurIPS), 3235–3246.
Rasmus, A., Berglund, M., Honkala, M., Valpola, H., & Raiko, T. (2015). Semi-supervised learning with ladder networks. In Advances in Neural Information Processing Systems (NeurIPS), 3546–3554.
Balasubramanian, A., & Gurushankar, N. (2020). Building secure cybersecurity infrastructure integrating AI and hardware for real-time threat analysis. International Journal of Core Engineering & Management, 6(7), 263–270.
Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems (NeurIPS), 1195–1204.
Sajjadi, M., Javanmardi, M., & Tasdizen, T. (2016). Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In Advances in Neural Information Processing Systems (NeurIPS), 1163–1171.
Berthelot, D., Carlini, N., Cubuk, E. D., Kurakin, A., Sohn, K., Zhang, H., & Raffel, C. (2019). MixMatch: A holistic approach to semi-supervised learning. In Advances in Neural Information Processing Systems (NeurIPS), 5049–5059.
Balasubramanian, A., & Gurushankar, N. (2019). AI-powered hardware fault detection and self-healing mechanisms. International Journal of Core Engineering & Management, 6(4), 23–30.
Chapelle, O., Schölkopf, B., & Zien, A. (2006). Semi-supervised learning. MIT Press.
Zhu, X. (2005). Semi-supervised learning literature survey. Computer Sciences Technical Report 1530, University of Wisconsin-Madison.
Grandvalet, Y., & Bengio, Y. (2005). Semi-supervised learning by entropy minimization. In Advances in Neural Information Processing Systems (NeurIPS), 529–536.
Gurushankar, N. (2020). Verification challenge in 3D integrated circuits (IC) design. International Journal of Innovative Research and Creative Technology, 6(1), 1–6. https://doi.org/10.5281/zenodo.14383858
Blum, A., & Mitchell, T. (1998). Combining labeled and unlabeled data with co-training. In Proceedings of the Eleventh Annual Conference on Computational Learning Theory (COLT), 92–100.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Sunitha Soumya Gopinath (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
