journal article·2023-07-31Open access

ReliaMatch: Semi-Supervised Classification with Reliable Match

Tao Jiang, Luyao Chen, Wanqing Chen, Wenjuan Meng, Peihan Qi

Applied Sciences· Volume 13· Issue 15

Abstract

Deep learning has been widely used in various tasks such as computer vision, natural language processing, predictive analysis, and recommendation systems in the past decade. However, practical scenarios often lack labeled data, posing challenges for traditional supervised methods. Semi-supervised classification methods address this by leveraging both labeled and unlabeled data to enhance model performance, but they face challenges in effectively utilizing unlabeled data and distinguishing reliable information from unreliable sources. This paper introduced ReliaMatch, a semi-supervised classification method that addresses these challenges by using a confidence threshold. It incorporates a curriculum learning stage, feature filtering, and pseudo-label filtering to improve classification accuracy and reliability. The feature filtering module eliminates ambiguous semantic features by comparing labeled and unlabeled data in the feature space. The pseudo-label filtering module removes unreliable pseudo-labels with low confidence, enhancing algorithm reliability. ReliaMatch employs a curriculum learning training mode, gradually increasing training dataset difficulty by combining selected samples and pseudo-labels with labeled data. This supervised approach enhances classification performance. Experimental results show that ReliaMatch effectively overcomes challenges associated with the underutilization of unlabeled data and the introduction of error information, outperforming the pseudo-label strategy in semi-supervised classification.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Anomaly Detection Techniques and Applications · Domain Adaptation and Few-Shot Learning · Machine Learning and Data Classification

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Cyber Engineering, Xidian University, Xi’an 710126, China

College of Information Engineering, Northwest A&F University, Xianyang 712100, China

State Key Laboratory of Integrated Service Networks, Xidian University, Xi’an 710071, China

Funding

National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities · Scientific Research Foundation of Northwest A&F University

References (45)

Show source-provided references
1. Going deeper with contextual CNN for hyperspectral image classification10.1109/TIP.2017.2725580 ↗
2. FedBKD: Heterogenous federated learning via bidirectional knowledge distillation for modulation classification in IoT-edge system10.1109/JSTSP.2022.3224597 ↗
3. Toward Next-Generation Signal Intelligence: A Hybrid Knowledge and Data-Driven Deep Learning Framework for Radio Signal Classification10.1109/TCCN.2023.3243899 ↗
4. Wang, Y., Long, M., Wang, J., Gao, Z., and Yu, P.S. (2017, January 4–9). PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs. Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA.
5. Bonet, B., and Koenig, S. (2015). Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA, 25–30 January 2015, AAAI Press.
6. Unsupervised anomaly detection with LSTM neural networks10.1109/TNNLS.2019.2935975 ↗
7. Detection tolerant black-Box adversarial attack against automatic Modulation Classification With Deep Learning10.1109/TR.2022.3161138 ↗
8. Semi-supervised learning (chapelle, o. et al., eds.; 2006) [book reviews]10.1109/TNN.2009.2015974 ↗
9. Rasmus, A., Berglund, M., Honkala, M., Valpola, H., and Raiko, T. (2015, January 7–12). Semi-supervised learning with ladder networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.10.1016/j.neunet.2014.09.004 ↗
10. Laine, S., and Aila, T. (2017, January 24–26). Temporal ensembling for semi-supervised learning. Proceedings of the 5th International Conference on Learning Representations, Toulon, France.
11. Virtual adversarial training: A regularization method for supervised and semi-supervised learning10.1109/TPAMI.2018.2858821 ↗
12. Zhou, D., Bousquet, O., Lal, T.N., Weston, J., and Schölkopf, B. (2004, January 13–18). Learning with local and global consistency. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
13. Iscen, A., Tolias, G., Avrithis, Y., and Chum, O. (2019, January 15–20). Label propagation for deep semi-supervised learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00521 ↗
14. Lee, D.H. (2013, January 16–21). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. Proceedings of the Workshop on Challenges in Representation Learning, Atlanta, GA, USA.
15. Tarvainen, A., and Valpola, H. (2017, January 24–26). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Proceedings of the 5th International Conference on Learning Representations, Toulon, France.
16. Arazo, E., Ortego, D., Albert, P., O’Connor, N.E., and McGuinness, K. (2020, January 19–24). Pseudo-labeling and confirmation bias in deep semi-supervised learning. Proceedings of the 2020 International Joint Conference on Neural Networks, Glasgow, UK.10.1109/IJCNN48605.2020.9207304 ↗
17. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., and Raffel, C. (2019, January 8–14). Mixmatch: A holistic approach to semi-supervised learning. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
18. Bengio, Y., Louradour, J., Collobert, R., and Weston, J. (2009, January 14–18). Curriculum learning. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.10.1145/1553374.1553380 ↗
19. Deng, J., Dong, W., Socher, R., Li, L., Li, K., and Fei-Fei, L. (2009). Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami, FL, USA, 20–25 June 2009, IEEE Computer Society.
20. Microsoft COCO: Common objects in context
21. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016). Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, IEEE Computer Society.
22. Wang, K., Yang, C., and Betke, M. Consistency regularization with high-dimensional non-adversarial source-guided perturbation for unsupervised domain adaptation in segmentation. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2–9 February 2021.
23. Abuduweili, A., Li, X., Shi, H., Xu, C., and Dou, D. (2021). Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, 19–25 June 2021, Computer Vision Foundation/IEEE.
24. Grandvalet, Y., and Bengio, Y. (2004, January 13–18). Semi-supervised learning by entropy minimization. Proceedings of the Advances in Neural Information Processing Systems 17, Neural Information Processing Systems, NIPS 2004, Vancouver, BC, Canada.
25. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, QC, Canada, 8–13 December 2014, Springer.
26. Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., and Garnett, R. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 5–10 December 2016, Cornell University.
27. Loshchilov, I., and Hutter, F. (2019, January 6–9). Decoupled weight decay regularization. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA. Available online: OpenReview.net.
28. Luo, Y., Zhu, J., Li, M., Ren, Y., and Zhang, B. (2018). Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, Computer Vision Foundation/IEEE Computer Society.
29. Zhang, H., Cissé, M., Dauphin, Y.N., and Lopez-Paz, D. (May, January 30). Mixup: Beyond empirical risk minimization. Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada.
30. Kraus, S. (2019, January 10–16). Interpolation consistency training for semi-supervised learning. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China. Available online: ijcai.org.
31. Semi-supervised cross-Modal retrieval with label prediction10.1109/TMM.2019.2954741 ↗
32. Deep clustering for unsupervised learning of visual features
33. Cascante-Bonilla, P., Tan, F., Qi, Y., and Ordonez, V. (2021, January 2–9). Curriculum labeling: Revisiting pseudo-labeling for semi-supervised learning. Proceedings of the 35th AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v35i8.16852 ↗
34. Demartini, G., Zuccon, G., Culpepper, J.S., Huang, Z., and Tong, H. (2021). Proceedings of the CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, 1–5 November 2021, ACM.
35. (2023, June 28). CIFAR10. Available online: http://www.cs.toronto.edu/~kriz/cifar.html.
36. (2023, June 28). SVHN. Available online: http://ufldl.stanford.edu/housenumbers/.
37. (2023, June 28). CIFAR100. Available online: http://www.cs.utoronto.ca/~kriz/cifar.html.
38. Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M.A. (2015, January 7–9). Striving for simplicity: The all convolutional net. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA.
39. Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.10.5244/C.30.87 ↗
40. Loshchilov, I., and Hutter, F. (2017, January 24–26). SGDR: Stochastic gradient descent with warm restarts. Proceedings of the 5th International Conference on Learning Representations, Toulon, France.
41. Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M., and Shinozaki, T. (2021, January 6–14). FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, Virtual.
42. Interpolation consistency training for semi-supervised learning10.1016/j.neunet.2021.10.008 ↗
43. Wang, Y., Guo, J., Song, S., and Huang, G. (2007). Meta-Semi: A Meta-learning Approach for Semi-supervised Learning. arXiv.
44. Wang, Y., Chen, H., Heng, Q., Hou, W., Fan, Y., Wu, Z., Wang, J., Savvides, M., Shinozaki, T., and Raj, B. (2023, January 1–5). FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning. Proceedings of the Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda. Available online: OpenReview.net.
45. Tang, H., and Jia, K. (2022). Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, 18–24 June 2022, IEEE.