<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maheshwari-etal-2022-fair">
    <titleInfo>
        <title>Fair NLP Models with Differentially Private Text Encoders</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gaurav</namePart>
        <namePart type="family">Maheshwari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pascal</namePart>
        <namePart type="family">Denis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikaela</namePart>
        <namePart type="family">Keller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aurélien</namePart>
        <namePart type="family">Bellet</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>Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon previous methods, and thus suggest that privacy and fairness can positively reinforce each other.</abstract>
    <identifier type="citekey">maheshwari-etal-2022-fair</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.514</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.514</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6913</start>
            <end>6930</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fair NLP Models with Differentially Private Text Encoders
%A Maheshwari, Gaurav
%A Denis, Pascal
%A Keller, Mikaela
%A Bellet, Aurélien
%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 maheshwari-etal-2022-fair
%X Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon previous methods, and thus suggest that privacy and fairness can positively reinforce each other.
%R 10.18653/v1/2022.findings-emnlp.514
%U https://aclanthology.org/2022.findings-emnlp.514
%U https://doi.org/10.18653/v1/2022.findings-emnlp.514
%P 6913-6930

Markdown (Informal)

[Fair NLP Models with Differentially Private Text Encoders](https://aclanthology.org/2022.findings-emnlp.514) (Maheshwari et al., Findings 2022)

• Fair NLP Models with Differentially Private Text Encoders (Maheshwari et al., Findings 2022)

ACL

• Gaurav Maheshwari, Pascal Denis, Mikaela Keller, and Aurélien Bellet. 2022. Fair NLP Models with Differentially Private Text Encoders. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6913–6930, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.