@inproceedings{guo-etal-2021-parameter,
title = "Parameter-Efficient Transfer Learning with Diff Pruning",
author = "Guo, Demi and
Rush, Alexander and
Kim, Yoon",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.378",
doi = "10.18653/v1/2021.acl-long.378",
pages = "4884--4896",
abstract = "The large size of pretrained networks makes them difficult to deploy for multiple tasks in storage-constrained settings. Diff pruning enables parameter-efficient transfer learning that scales well with new tasks. The approach learns a task-specific {``}diff{''} vector that extends the original pretrained parameters. This diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. As the number of tasks increases, diff pruning remains parameter-efficient, as it requires storing only a small diff vector for each task. Since it does not require access to all tasks during training, it is attractive in on-device deployment settings where tasks arrive in stream or even from different providers. Diff pruning can match the performance of finetuned baselines on the GLUE benchmark while only modifying 0.5{\%} of the pretrained model{'}s parameters per task and scales favorably in comparison to popular pruning approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2021-parameter">
<titleInfo>
<title>Parameter-Efficient Transfer Learning with Diff Pruning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Demi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The large size of pretrained networks makes them difficult to deploy for multiple tasks in storage-constrained settings. Diff pruning enables parameter-efficient transfer learning that scales well with new tasks. The approach learns a task-specific “diff” vector that extends the original pretrained parameters. This diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. As the number of tasks increases, diff pruning remains parameter-efficient, as it requires storing only a small diff vector for each task. Since it does not require access to all tasks during training, it is attractive in on-device deployment settings where tasks arrive in stream or even from different providers. Diff pruning can match the performance of finetuned baselines on the GLUE benchmark while only modifying 0.5% of the pretrained model’s parameters per task and scales favorably in comparison to popular pruning approaches.</abstract>
<identifier type="citekey">guo-etal-2021-parameter</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.378</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.378</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4884</start>
<end>4896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter-Efficient Transfer Learning with Diff Pruning
%A Guo, Demi
%A Rush, Alexander
%A Kim, Yoon
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F guo-etal-2021-parameter
%X The large size of pretrained networks makes them difficult to deploy for multiple tasks in storage-constrained settings. Diff pruning enables parameter-efficient transfer learning that scales well with new tasks. The approach learns a task-specific “diff” vector that extends the original pretrained parameters. This diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. As the number of tasks increases, diff pruning remains parameter-efficient, as it requires storing only a small diff vector for each task. Since it does not require access to all tasks during training, it is attractive in on-device deployment settings where tasks arrive in stream or even from different providers. Diff pruning can match the performance of finetuned baselines on the GLUE benchmark while only modifying 0.5% of the pretrained model’s parameters per task and scales favorably in comparison to popular pruning approaches.
%R 10.18653/v1/2021.acl-long.378
%U https://aclanthology.org/2021.acl-long.378
%U https://doi.org/10.18653/v1/2021.acl-long.378
%P 4884-4896
Markdown (Informal)
[Parameter-Efficient Transfer Learning with Diff Pruning](https://aclanthology.org/2021.acl-long.378) (Guo et al., ACL-IJCNLP 2021)
ACL
- Demi Guo, Alexander Rush, and Yoon Kim. 2021. Parameter-Efficient Transfer Learning with Diff Pruning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4884–4896, Online. Association for Computational Linguistics.