<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kobayashi-etal-2022-diverse">
    <titleInfo>
        <title>Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sosuke</namePart>
        <namePart type="family">Kobayashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shun</namePart>
        <namePart type="family">Kiyono</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Suzuki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kentaro</namePart>
        <namePart type="family">Inui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of BigScience Episode #5 – Workshop on Challenges &amp; Perspectives in Creating Large Language Models</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Angela</namePart>
            <namePart type="family">Fan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Suzana</namePart>
            <namePart type="family">Ilic</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thomas</namePart>
            <namePart type="family">Wolf</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthias</namePart>
            <namePart type="family">Gallé</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">virtual+Dublin</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble members. This paper proposes Multi-Ticket Ensemble, which finetunes different subnetworks of a single pretrained model and ensembles them. We empirically demonstrated that winning-ticket subnetworks produced more diverse predictions than dense networks and their ensemble outperformed the standard ensemble in some tasks when accurate lottery tickets are found on the tasks.</abstract>
    <identifier type="citekey">kobayashi-etal-2022-diverse</identifier>
    <identifier type="doi">10.18653/v1/2022.bigscience-1.4</identifier>
    <location>
        <url>https://aclanthology.org/2022.bigscience-1.4</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>42</start>
            <end>50</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
%A Kobayashi, Sosuke
%A Kiyono, Shun
%A Suzuki, Jun
%A Inui, Kentaro
%Y Fan, Angela
%Y Ilic, Suzana
%Y Wolf, Thomas
%Y Gallé, Matthias
%S Proceedings of BigScience Episode #5 – Workshop on Challenges & Perspectives in Creating Large Language Models
%D 2022
%8 May
%I Association for Computational Linguistics
%C virtual+Dublin
%F kobayashi-etal-2022-diverse
%X Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble members. This paper proposes Multi-Ticket Ensemble, which finetunes different subnetworks of a single pretrained model and ensembles them. We empirically demonstrated that winning-ticket subnetworks produced more diverse predictions than dense networks and their ensemble outperformed the standard ensemble in some tasks when accurate lottery tickets are found on the tasks.
%R 10.18653/v1/2022.bigscience-1.4
%U https://aclanthology.org/2022.bigscience-1.4
%U https://doi.org/10.18653/v1/2022.bigscience-1.4
%P 42-50

Markdown (Informal)

[Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model](https://aclanthology.org/2022.bigscience-1.4) (Kobayashi et al., BigScience 2022)

• Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model (Kobayashi et al., BigScience 2022)

ACL

• Sosuke Kobayashi, Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2022. Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model. In Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models, pages 42–50, virtual+Dublin. Association for Computational Linguistics.