@inproceedings{wang-etal-2024-pruning,
title = "Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models",
author = "Wang, Pingjie and
Liu, Hongcheng and
Wang, Yanfeng and
Wang, Yu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1162",
pages = "13279--13289",
abstract = "Structured pruning is an effective technique for compressing pre-trained language models (PLMs), reducing model size and improving inference speed for efficient deployment. However, most of existing pruning algorithms require retraining, leading to additional computational overhead. While some retraining-free approaches have been proposed for classification tasks, they still require a fully fine-tuned model for the task, and may cause catastrophic performance degradation on generative tasks. To address these challenges, we propose P-pruning (pre-pruning), an innovative task-specific compression framework. P-pruning prunes redundant modules of PLMs before fine-tuning, reducing the costs associated with fine-tuning. We also introduce a pruning algorithm for this framework, which includes two techniques: (1) module clustering, which clusters the outputs of all heads and neurons based on the task input; and (2) centroid selection, which identifies the most salient element in each cluster and prunes the others. We apply our method to BERT and GPT-2 and evaluate its effectiveness on GLUE, SQuAD, WikiText-2, WikiText-103, and PTB datasets. Experimental results demonstrate that our approach achieves higher performance in both classification and generative tasks, while also reducing the time required for fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-pruning">
<titleInfo>
<title>Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pingjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongcheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanfeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Structured pruning is an effective technique for compressing pre-trained language models (PLMs), reducing model size and improving inference speed for efficient deployment. However, most of existing pruning algorithms require retraining, leading to additional computational overhead. While some retraining-free approaches have been proposed for classification tasks, they still require a fully fine-tuned model for the task, and may cause catastrophic performance degradation on generative tasks. To address these challenges, we propose P-pruning (pre-pruning), an innovative task-specific compression framework. P-pruning prunes redundant modules of PLMs before fine-tuning, reducing the costs associated with fine-tuning. We also introduce a pruning algorithm for this framework, which includes two techniques: (1) module clustering, which clusters the outputs of all heads and neurons based on the task input; and (2) centroid selection, which identifies the most salient element in each cluster and prunes the others. We apply our method to BERT and GPT-2 and evaluate its effectiveness on GLUE, SQuAD, WikiText-2, WikiText-103, and PTB datasets. Experimental results demonstrate that our approach achieves higher performance in both classification and generative tasks, while also reducing the time required for fine-tuning.</abstract>
<identifier type="citekey">wang-etal-2024-pruning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1162</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13279</start>
<end>13289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models
%A Wang, Pingjie
%A Liu, Hongcheng
%A Wang, Yanfeng
%A Wang, Yu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F wang-etal-2024-pruning
%X Structured pruning is an effective technique for compressing pre-trained language models (PLMs), reducing model size and improving inference speed for efficient deployment. However, most of existing pruning algorithms require retraining, leading to additional computational overhead. While some retraining-free approaches have been proposed for classification tasks, they still require a fully fine-tuned model for the task, and may cause catastrophic performance degradation on generative tasks. To address these challenges, we propose P-pruning (pre-pruning), an innovative task-specific compression framework. P-pruning prunes redundant modules of PLMs before fine-tuning, reducing the costs associated with fine-tuning. We also introduce a pruning algorithm for this framework, which includes two techniques: (1) module clustering, which clusters the outputs of all heads and neurons based on the task input; and (2) centroid selection, which identifies the most salient element in each cluster and prunes the others. We apply our method to BERT and GPT-2 and evaluate its effectiveness on GLUE, SQuAD, WikiText-2, WikiText-103, and PTB datasets. Experimental results demonstrate that our approach achieves higher performance in both classification and generative tasks, while also reducing the time required for fine-tuning.
%U https://aclanthology.org/2024.lrec-main.1162
%P 13279-13289
Markdown (Informal)
[Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models](https://aclanthology.org/2024.lrec-main.1162) (Wang et al., LREC-COLING 2024)
ACL