@inproceedings{wang-etal-2021-secure,
title = "A Secure and Efficient Federated Learning Framework for {NLP}",
author = "Wang, Chenghong and
Deng, Jieren and
Meng, Xianrui and
Wang, Yijue and
Li, Ji and
Lin, Sheng and
Han, Shuo and
Miao, Fei and
Rajasekaran, Sanguthevar and
Ding, Caiwen",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.606",
doi = "10.18653/v1/2021.emnlp-main.606",
pages = "7676--7682",
abstract = "In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient federated learning framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-secure">
<titleInfo>
<title>A Secure and Efficient Federated Learning Framework for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenghong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieren</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianrui</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanguthevar</namePart>
<namePart type="family">Rajasekaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiwen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient federated learning framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts.</abstract>
<identifier type="citekey">wang-etal-2021-secure</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.606</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.606</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>7676</start>
<end>7682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Secure and Efficient Federated Learning Framework for NLP
%A Wang, Chenghong
%A Deng, Jieren
%A Meng, Xianrui
%A Wang, Yijue
%A Li, Ji
%A Lin, Sheng
%A Han, Shuo
%A Miao, Fei
%A Rajasekaran, Sanguthevar
%A Ding, Caiwen
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F wang-etal-2021-secure
%X In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient federated learning framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts.
%R 10.18653/v1/2021.emnlp-main.606
%U https://aclanthology.org/2021.emnlp-main.606
%U https://doi.org/10.18653/v1/2021.emnlp-main.606
%P 7676-7682
Markdown (Informal)
[A Secure and Efficient Federated Learning Framework for NLP](https://aclanthology.org/2021.emnlp-main.606) (Wang et al., EMNLP 2021)
ACL
- Chenghong Wang, Jieren Deng, Xianrui Meng, Yijue Wang, Ji Li, Sheng Lin, Shuo Han, Fei Miao, Sanguthevar Rajasekaran, and Caiwen Ding. 2021. A Secure and Efficient Federated Learning Framework for NLP. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7676–7682, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.