@inproceedings{sirbu-etal-2025-multimatch,
title = "{M}ulti{M}atch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification",
author = "Sirbu, Iustin and
Popovici, Robert-Adrian and
Caragea, Cornelia and
Trausan-Matu, Stefan and
Rebedea, Traian",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.139/",
pages = "2792--2808",
ISBN = "979-8-89176-332-6",
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 three-fold 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 **Multi**head Co-training, self-adaptive thresholds from Free**Match**, and Average Pseudo-Margins from Margin**Match** $-$ 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sirbu-etal-2025-multimatch">
<titleInfo>
<title>MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iustin</namePart>
<namePart type="family">Sirbu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert-Adrian</namePart>
<namePart type="family">Popovici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Trausan-Matu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Traian</namePart>
<namePart type="family">Rebedea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<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 three-fold 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 **Multi**head Co-training, self-adaptive thresholds from Free**Match**, and Average Pseudo-Margins from Margin**Match** - 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.</abstract>
<identifier type="citekey">sirbu-etal-2025-multimatch</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.139/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2792</start>
<end>2808</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
%A Sirbu, Iustin
%A Popovici, Robert-Adrian
%A Caragea, Cornelia
%A Trausan-Matu, Stefan
%A Rebedea, Traian
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F sirbu-etal-2025-multimatch
%X 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 three-fold 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 **Multi**head Co-training, self-adaptive thresholds from Free**Match**, and Average Pseudo-Margins from Margin**Match** - 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.
%U https://aclanthology.org/2025.emnlp-main.139/
%P 2792-2808
Markdown (Informal)
[MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification](https://aclanthology.org/2025.emnlp-main.139/) (Sirbu et al., EMNLP 2025)
ACL