MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
This addresses semi-supervised learning for text classification, offering incremental improvements in robustness and performance for real-world applications.
The paper tackles semi-supervised text classification by introducing MultiMatch, which combines co-training and consistency regularization with a pseudo-label weighting module, achieving state-of-the-art results on 8 out of 10 benchmark setups and showing 3.26% improvement in imbalanced settings.
We introduce MultiMatch, a novel semi-supervised learning (SSL) algorithm combining the paradigms of co-training and consistency regularization with pseudo-labeling. At its core, MultiMatch features a pseudo-label weighting module designed for selecting and filtering pseudo-labels based on head agreement and model confidence, and weighting them according to the perceived classification difficulty. This novel module enhances and unifies three existing techniques -- heads agreement from Multihead Co-training, self-adaptive thresholds from FreeMatch, and Average Pseudo-Margins from MarginMatch -- resulting in a holistic approach that improves robustness and performance in SSL settings. Experimental results on benchmark datasets highlight the superior performance of MultiMatch, i.e., MultiMatch achieves state-of-the-art results on 8 out of 10 setups from 5 natural language processing datasets and ranks first according to the Friedman test among 21 methods. Furthermore, MultiMatch demonstrates exceptional robustness in highly imbalanced settings, outperforming the second-best approach by 3.26%, a critical advantage for real-world text classification tasks. Our code is available on GitHub.