@inproceedings{mao-etal-2025-lightweight,
title = "Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence",
author = "Mao, Qianren and
Jiang, Weifeng and
Liu, Junnan and
Lin, Chenghua and
Li, Qian and
Wen, Xianqing and
Li, Jianxin and
Lu, Jinhu",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.309/",
doi = "10.18653/v1/2025.findings-naacl.309",
pages = "5571--5585",
ISBN = "979-8-89176-195-7",
abstract = "The semi-supervised learning (SSL) strategy in lightweight models requires reducing annotated samples and facilitating cost-effective inference. However, the constraint on model parameters, imposed by the scarcity of training labels, limits the SSL performance. In this paper, we introduce PS-NET, a novel framework tailored for semi-supervised text mining with lightweight models. PS-NET incorporates online distillation to train lightweight student models by imitating the Teacher model. It also integrates an ensemble of student peers that collaboratively instruct each other. Additionally, PS-NET implements a constant adversarial perturbation schema to further self-augmentation by progressive generalizing. Our PS-NET, equipped with a 2-layer distilled BERT, exhibits notable performance enhancements over SOTA lightweight SSL frameworks of FLiText and Disco in SSL text classification with extremely rare labelled data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-etal-2025-lightweight">
<titleInfo>
<title>Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianren</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weifeng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianqing</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinhu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>The semi-supervised learning (SSL) strategy in lightweight models requires reducing annotated samples and facilitating cost-effective inference. However, the constraint on model parameters, imposed by the scarcity of training labels, limits the SSL performance. In this paper, we introduce PS-NET, a novel framework tailored for semi-supervised text mining with lightweight models. PS-NET incorporates online distillation to train lightweight student models by imitating the Teacher model. It also integrates an ensemble of student peers that collaboratively instruct each other. Additionally, PS-NET implements a constant adversarial perturbation schema to further self-augmentation by progressive generalizing. Our PS-NET, equipped with a 2-layer distilled BERT, exhibits notable performance enhancements over SOTA lightweight SSL frameworks of FLiText and Disco in SSL text classification with extremely rare labelled data.</abstract>
<identifier type="citekey">mao-etal-2025-lightweight</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.309</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.309/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5571</start>
<end>5585</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
%A Mao, Qianren
%A Jiang, Weifeng
%A Liu, Junnan
%A Lin, Chenghua
%A Li, Qian
%A Wen, Xianqing
%A Li, Jianxin
%A Lu, Jinhu
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F mao-etal-2025-lightweight
%X The semi-supervised learning (SSL) strategy in lightweight models requires reducing annotated samples and facilitating cost-effective inference. However, the constraint on model parameters, imposed by the scarcity of training labels, limits the SSL performance. In this paper, we introduce PS-NET, a novel framework tailored for semi-supervised text mining with lightweight models. PS-NET incorporates online distillation to train lightweight student models by imitating the Teacher model. It also integrates an ensemble of student peers that collaboratively instruct each other. Additionally, PS-NET implements a constant adversarial perturbation schema to further self-augmentation by progressive generalizing. Our PS-NET, equipped with a 2-layer distilled BERT, exhibits notable performance enhancements over SOTA lightweight SSL frameworks of FLiText and Disco in SSL text classification with extremely rare labelled data.
%R 10.18653/v1/2025.findings-naacl.309
%U https://aclanthology.org/2025.findings-naacl.309/
%U https://doi.org/10.18653/v1/2025.findings-naacl.309
%P 5571-5585
Markdown (Informal)
[Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence](https://aclanthology.org/2025.findings-naacl.309/) (Mao et al., Findings 2025)
ACL
- Qianren Mao, Weifeng Jiang, Junnan Liu, Chenghua Lin, Qian Li, Xianqing Wen, Jianxin Li, and Jinhu Lu. 2025. Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 5571–5585, Albuquerque, New Mexico. Association for Computational Linguistics.