MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
Abstract
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.
Cite
@article{arxiv.2506.07801,
title = {MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification},
author = {Iustin Sirbu and Robert-Adrian Popovici and Cornelia Caragea and Stefan Trausan-Matu and Traian Rebedea},
journal= {arXiv preprint arXiv:2506.07801},
year = {2025}
}
Comments
This is the camera-ready version of the paper, accepted for publication in the Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)