@inproceedings{wang-etal-2024-personalized,
title = "Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning",
author = "Wang, Rui and
Yu, Tong and
Zhang, Ruiyi and
Kim, Sungchul and
Rossi, Ryan and
Zhao, Handong and
Wu, Junda and
Mitra, Subrata and
Yao, Lina and
Henao, Ricardo",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.286",
doi = "10.18653/v1/2024.findings-naacl.286",
pages = "4597--4612",
abstract = "In this paper, we study personalized federated learning for text classification with Pretrained Language Models (PLMs). We identify two challenges in efficiently leveraging PLMs for personalized federated learning: 1) Communication. PLMs are usually large in size, e.g., with hundreds of millions of parameters, inducing huge communication cost in a federated setting. 2) Local Training. Training with PLMs generally requires back-propagation, during which memory consumption can be several times that of the forward-propagation. This may not be affordable when the PLMs are trained locally on the clients that are resource constrained, e.g., mobile devices with limited access to memory resources. Additionally, the proprietary PLMs can be provided as concealed APIs, for which the back-propagation operations may not be available. In solving these, we propose a training framework that includes an approach of discrete local search for gradient-free local training, along with a compression mechanism inspired from the linear word analogy that allows communicating with discretely indexed tokens, thus significantly reducing the communication cost. Experiments show that our gradient-free framework achieves superior performance compared with baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-personalized">
<titleInfo>
<title>Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungchul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Handong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junda</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subrata</namePart>
<namePart type="family">Mitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we study personalized federated learning for text classification with Pretrained Language Models (PLMs). We identify two challenges in efficiently leveraging PLMs for personalized federated learning: 1) Communication. PLMs are usually large in size, e.g., with hundreds of millions of parameters, inducing huge communication cost in a federated setting. 2) Local Training. Training with PLMs generally requires back-propagation, during which memory consumption can be several times that of the forward-propagation. This may not be affordable when the PLMs are trained locally on the clients that are resource constrained, e.g., mobile devices with limited access to memory resources. Additionally, the proprietary PLMs can be provided as concealed APIs, for which the back-propagation operations may not be available. In solving these, we propose a training framework that includes an approach of discrete local search for gradient-free local training, along with a compression mechanism inspired from the linear word analogy that allows communicating with discretely indexed tokens, thus significantly reducing the communication cost. Experiments show that our gradient-free framework achieves superior performance compared with baselines.</abstract>
<identifier type="citekey">wang-etal-2024-personalized</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.286</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.286</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4597</start>
<end>4612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning
%A Wang, Rui
%A Yu, Tong
%A Zhang, Ruiyi
%A Kim, Sungchul
%A Rossi, Ryan
%A Zhao, Handong
%A Wu, Junda
%A Mitra, Subrata
%A Yao, Lina
%A Henao, Ricardo
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-etal-2024-personalized
%X In this paper, we study personalized federated learning for text classification with Pretrained Language Models (PLMs). We identify two challenges in efficiently leveraging PLMs for personalized federated learning: 1) Communication. PLMs are usually large in size, e.g., with hundreds of millions of parameters, inducing huge communication cost in a federated setting. 2) Local Training. Training with PLMs generally requires back-propagation, during which memory consumption can be several times that of the forward-propagation. This may not be affordable when the PLMs are trained locally on the clients that are resource constrained, e.g., mobile devices with limited access to memory resources. Additionally, the proprietary PLMs can be provided as concealed APIs, for which the back-propagation operations may not be available. In solving these, we propose a training framework that includes an approach of discrete local search for gradient-free local training, along with a compression mechanism inspired from the linear word analogy that allows communicating with discretely indexed tokens, thus significantly reducing the communication cost. Experiments show that our gradient-free framework achieves superior performance compared with baselines.
%R 10.18653/v1/2024.findings-naacl.286
%U https://aclanthology.org/2024.findings-naacl.286
%U https://doi.org/10.18653/v1/2024.findings-naacl.286
%P 4597-4612
Markdown (Informal)
[Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning](https://aclanthology.org/2024.findings-naacl.286) (Wang et al., Findings 2024)
ACL
- Rui Wang, Tong Yu, Ruiyi Zhang, Sungchul Kim, Ryan Rossi, Handong Zhao, Junda Wu, Subrata Mitra, Lina Yao, and Ricardo Henao. 2024. Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4597–4612, Mexico City, Mexico. Association for Computational Linguistics.