<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akbartajari-etal-2022-empirical">
    <titleInfo>
        <title>An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">AkbarTajari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sara</namePart>
        <namePart type="family">Rajaee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="given">Taher</namePart>
        <namePart type="family">Pilehvar</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>Parameter-efficient fine-tuning has garnered lots of attention in recent studies. On this subject, we investigate the capability of different transformer modules in transferring knowledge from a pre-trained model to a downstream task. Our empirical results suggest that every transformer module is a winning ticket such that fine-tuning the specific module while the rest of the network is frozen achieves a comparable performance to the full fine-tuning case. Among different modules in LMs, LayerNorms exhibit a significant capacity for transfer learning to the extent that with only 0.003% updateable parameters in the layer-wise analysis, they can show acceptable performance on various target tasks. We argue that the performance of LayerNorms could be attributed to their high-magnitude weights compared to other components in a pre-trained model.</abstract>
    <identifier type="citekey">akbartajari-etal-2022-empirical</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.726</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.726</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10617</start>
            <end>10625</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuning
%A AkbarTajari, Mohammad
%A Rajaee, Sara
%A Pilehvar, Mohammad Taher
%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 akbartajari-etal-2022-empirical
%X Parameter-efficient fine-tuning has garnered lots of attention in recent studies. On this subject, we investigate the capability of different transformer modules in transferring knowledge from a pre-trained model to a downstream task. Our empirical results suggest that every transformer module is a winning ticket such that fine-tuning the specific module while the rest of the network is frozen achieves a comparable performance to the full fine-tuning case. Among different modules in LMs, LayerNorms exhibit a significant capacity for transfer learning to the extent that with only 0.003% updateable parameters in the layer-wise analysis, they can show acceptable performance on various target tasks. We argue that the performance of LayerNorms could be attributed to their high-magnitude weights compared to other components in a pre-trained model.
%R 10.18653/v1/2022.emnlp-main.726
%U https://aclanthology.org/2022.emnlp-main.726
%U https://doi.org/10.18653/v1/2022.emnlp-main.726
%P 10617-10625

Markdown (Informal)

[An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuning](https://aclanthology.org/2022.emnlp-main.726) (AkbarTajari et al., EMNLP 2022)

• An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuning (AkbarTajari et al., EMNLP 2022)

ACL

• Mohammad AkbarTajari, Sara Rajaee, and Mohammad Taher Pilehvar. 2022. An Empirical Study on the Transferability of Transformer Modules in Parameter-efficient Fine-tuning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10617–10625, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.