@inproceedings{huang-etal-2022-fpt,
title = "{FPT}: Improving Prompt Tuning Efficiency via Progressive Training",
author = "Huang, Yufei and
Qin, Yujia and
Wang, Huadong and
Yin, Yichun and
Sun, Maosong and
Liu, Zhiyuan and
Liu, Qun",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.511",
doi = "10.18653/v1/2022.findings-emnlp.511",
pages = "6877--6887",
abstract = "Recently, prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs). Despite extensively reducing the number of tunable parameters and achieving satisfying performance, PT is training-inefficient due to its slow convergence. To improve PT{'}s training efficiency, we first make some novel observations about the prompt transferability of {``}partial PLMs{''}, which are defined by compressing a PLM in depth or width. We observe that the soft prompts learned by different partial PLMs of various sizes are similar in the parameter space, implying that these soft prompts could potentially be transferred among partial PLMs. Inspired by these observations, we propose Fast Prompt Tuning (FPT), which starts by conducting PT using a small-scale partial PLM, and then progressively expands its depth and width until the full-model size. After each expansion, we recycle the previously learned soft prompts as initialization for the enlarged partial PLM and then proceed PT. We demonstrate the feasibility of FPT on 5 tasks and show that FPT could save over 30{\%} training computations while achieving comparable performance. The codes are publicly available at https://github.com/thunlp/FastPromptTuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-fpt">
<titleInfo>
<title>FPT: Improving Prompt Tuning Efficiency via Progressive Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Huang</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">Huadong</namePart>
<namePart type="family">Wang</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">Maosong</namePart>
<namePart type="family">Sun</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>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs). Despite extensively reducing the number of tunable parameters and achieving satisfying performance, PT is training-inefficient due to its slow convergence. To improve PT’s training efficiency, we first make some novel observations about the prompt transferability of “partial PLMs”, which are defined by compressing a PLM in depth or width. We observe that the soft prompts learned by different partial PLMs of various sizes are similar in the parameter space, implying that these soft prompts could potentially be transferred among partial PLMs. Inspired by these observations, we propose Fast Prompt Tuning (FPT), which starts by conducting PT using a small-scale partial PLM, and then progressively expands its depth and width until the full-model size. After each expansion, we recycle the previously learned soft prompts as initialization for the enlarged partial PLM and then proceed PT. We demonstrate the feasibility of FPT on 5 tasks and show that FPT could save over 30% training computations while achieving comparable performance. The codes are publicly available at https://github.com/thunlp/FastPromptTuning.</abstract>
<identifier type="citekey">huang-etal-2022-fpt</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.511</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.511</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6877</start>
<end>6887</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FPT: Improving Prompt Tuning Efficiency via Progressive Training
%A Huang, Yufei
%A Qin, Yujia
%A Wang, Huadong
%A Yin, Yichun
%A Sun, Maosong
%A Liu, Zhiyuan
%A Liu, Qun
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F huang-etal-2022-fpt
%X Recently, prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs). Despite extensively reducing the number of tunable parameters and achieving satisfying performance, PT is training-inefficient due to its slow convergence. To improve PT’s training efficiency, we first make some novel observations about the prompt transferability of “partial PLMs”, which are defined by compressing a PLM in depth or width. We observe that the soft prompts learned by different partial PLMs of various sizes are similar in the parameter space, implying that these soft prompts could potentially be transferred among partial PLMs. Inspired by these observations, we propose Fast Prompt Tuning (FPT), which starts by conducting PT using a small-scale partial PLM, and then progressively expands its depth and width until the full-model size. After each expansion, we recycle the previously learned soft prompts as initialization for the enlarged partial PLM and then proceed PT. We demonstrate the feasibility of FPT on 5 tasks and show that FPT could save over 30% training computations while achieving comparable performance. The codes are publicly available at https://github.com/thunlp/FastPromptTuning.
%R 10.18653/v1/2022.findings-emnlp.511
%U https://aclanthology.org/2022.findings-emnlp.511
%U https://doi.org/10.18653/v1/2022.findings-emnlp.511
%P 6877-6887
Markdown (Informal)
[FPT: Improving Prompt Tuning Efficiency via Progressive Training](https://aclanthology.org/2022.findings-emnlp.511) (Huang et al., Findings 2022)
ACL
- Yufei Huang, Yujia Qin, Huadong Wang, Yichun Yin, Maosong Sun, Zhiyuan Liu, and Qun Liu. 2022. FPT: Improving Prompt Tuning Efficiency via Progressive Training. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6877–6887, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.