@inproceedings{chen-etal-2022-bert2bert,
title = "bert2{BERT}: Towards Reusable Pretrained Language Models",
author = "Chen, Cheng and
Yin, Yichun and
Shang, Lifeng and
Jiang, Xin and
Qin, Yujia and
Wang, Fengyu and
Wang, Zhi and
Chen, Xiao and
Liu, Zhiyuan and
Liu, Qun",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.151/",
doi = "10.18653/v1/2022.acl-long.151",
pages = "2134--2148",
abstract = "In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources, and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful. In this paper, we propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model. Specifically, we extend the previous function-preserving method proposed in computer vision on the Transformer-based language model, and further improve it by proposing a novel method, advanced knowledge for large model`s initialization. In addition, a two-stage learning method is proposed to further accelerate the pre-training. We conduct extensive experiments on representative PLMs (e.g., BERT and GPT) and demonstrate that (1) our method can save a significant amount of training cost compared with baselines including learning from scratch, StackBERT and MSLT; (2) our method is generic and applicable to different types of pre-trained models. In particular, bert2BERT saves about 45{\%} and 47{\%} computational cost of pre-training BERT$_{\rm BASE}$ and GPT$_{\rm BASE}$ by reusing the models of almost their half sizes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-bert2bert">
<titleInfo>
<title>bert2BERT: Towards Reusable Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichun</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujia</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources, and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful. In this paper, we propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model. Specifically, we extend the previous function-preserving method proposed in computer vision on the Transformer-based language model, and further improve it by proposing a novel method, advanced knowledge for large model‘s initialization. In addition, a two-stage learning method is proposed to further accelerate the pre-training. We conduct extensive experiments on representative PLMs (e.g., BERT and GPT) and demonstrate that (1) our method can save a significant amount of training cost compared with baselines including learning from scratch, StackBERT and MSLT; (2) our method is generic and applicable to different types of pre-trained models. In particular, bert2BERT saves about 45% and 47% computational cost of pre-training BERT_ BASE and GPT_ BASE by reusing the models of almost their half sizes.</abstract>
<identifier type="citekey">chen-etal-2022-bert2bert</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.151</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.151/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2134</start>
<end>2148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T bert2BERT: Towards Reusable Pretrained Language Models
%A Chen, Cheng
%A Yin, Yichun
%A Shang, Lifeng
%A Jiang, Xin
%A Qin, Yujia
%A Wang, Fengyu
%A Wang, Zhi
%A Chen, Xiao
%A Liu, Zhiyuan
%A Liu, Qun
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-etal-2022-bert2bert
%X In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources, and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful. In this paper, we propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model. Specifically, we extend the previous function-preserving method proposed in computer vision on the Transformer-based language model, and further improve it by proposing a novel method, advanced knowledge for large model‘s initialization. In addition, a two-stage learning method is proposed to further accelerate the pre-training. We conduct extensive experiments on representative PLMs (e.g., BERT and GPT) and demonstrate that (1) our method can save a significant amount of training cost compared with baselines including learning from scratch, StackBERT and MSLT; (2) our method is generic and applicable to different types of pre-trained models. In particular, bert2BERT saves about 45% and 47% computational cost of pre-training BERT_ BASE and GPT_ BASE by reusing the models of almost their half sizes.
%R 10.18653/v1/2022.acl-long.151
%U https://aclanthology.org/2022.acl-long.151/
%U https://doi.org/10.18653/v1/2022.acl-long.151
%P 2134-2148
Markdown (Informal)
[bert2BERT: Towards Reusable Pretrained Language Models](https://aclanthology.org/2022.acl-long.151/) (Chen et al., ACL 2022)
ACL
- Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, and Qun Liu. 2022. bert2BERT: Towards Reusable Pretrained Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2134–2148, Dublin, Ireland. Association for Computational Linguistics.