@inproceedings{zhang-etal-2022-federated,
title = "Federated Model Decomposition with Private Vocabulary for Text Classification",
author = "Zhang, Zhuo and
Hu, Xiangjing and
Qu, Lizhen and
Wang, Qifan and
Xu, Zenglin",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.430",
doi = "10.18653/v1/2022.emnlp-main.430",
pages = "6413--6425",
abstract = "With the necessity of privacy protection, it becomes increasingly vital to train deep neural models in a federated learning manner for natural language processing (NLP) tasks. However, recent studies show eavesdroppers (i.e., dishonest servers) can still reconstruct the private input in federated learning (FL). Such a data reconstruction attack relies on the mappings between vocabulary and associated word embedding in NLP tasks, which are unfortunately less studied in current FL methods. In this paper, we propose a fedrated model decomposition method that protects the privacy of vocabularies, shorted as FEDEVOCAB. In FEDEVOCAB, each participant keeps the local embedding layer in the local device and detaches the local embedding parameters from federated aggregation. However, it is challenging to train an accurate NLP model when the private mappings are unknown and vary across participants in a cross-device FL setting. To address this problem, we further propose an adaptive updating technique to improve the performance of local models. Experimental results show that FEDEVOCAB maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-federated">
<titleInfo>
<title>Federated Model Decomposition with Private Vocabulary for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangjing</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zenglin</namePart>
<namePart type="family">Xu</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>With the necessity of privacy protection, it becomes increasingly vital to train deep neural models in a federated learning manner for natural language processing (NLP) tasks. However, recent studies show eavesdroppers (i.e., dishonest servers) can still reconstruct the private input in federated learning (FL). Such a data reconstruction attack relies on the mappings between vocabulary and associated word embedding in NLP tasks, which are unfortunately less studied in current FL methods. In this paper, we propose a fedrated model decomposition method that protects the privacy of vocabularies, shorted as FEDEVOCAB. In FEDEVOCAB, each participant keeps the local embedding layer in the local device and detaches the local embedding parameters from federated aggregation. However, it is challenging to train an accurate NLP model when the private mappings are unknown and vary across participants in a cross-device FL setting. To address this problem, we further propose an adaptive updating technique to improve the performance of local models. Experimental results show that FEDEVOCAB maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods.</abstract>
<identifier type="citekey">zhang-etal-2022-federated</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.430</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.430</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6413</start>
<end>6425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Federated Model Decomposition with Private Vocabulary for Text Classification
%A Zhang, Zhuo
%A Hu, Xiangjing
%A Qu, Lizhen
%A Wang, Qifan
%A Xu, Zenglin
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-federated
%X With the necessity of privacy protection, it becomes increasingly vital to train deep neural models in a federated learning manner for natural language processing (NLP) tasks. However, recent studies show eavesdroppers (i.e., dishonest servers) can still reconstruct the private input in federated learning (FL). Such a data reconstruction attack relies on the mappings between vocabulary and associated word embedding in NLP tasks, which are unfortunately less studied in current FL methods. In this paper, we propose a fedrated model decomposition method that protects the privacy of vocabularies, shorted as FEDEVOCAB. In FEDEVOCAB, each participant keeps the local embedding layer in the local device and detaches the local embedding parameters from federated aggregation. However, it is challenging to train an accurate NLP model when the private mappings are unknown and vary across participants in a cross-device FL setting. To address this problem, we further propose an adaptive updating technique to improve the performance of local models. Experimental results show that FEDEVOCAB maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods.
%R 10.18653/v1/2022.emnlp-main.430
%U https://aclanthology.org/2022.emnlp-main.430
%U https://doi.org/10.18653/v1/2022.emnlp-main.430
%P 6413-6425
Markdown (Informal)
[Federated Model Decomposition with Private Vocabulary for Text Classification](https://aclanthology.org/2022.emnlp-main.430) (Zhang et al., EMNLP 2022)
ACL