<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2022-tiny">
    <titleInfo>
        <title>Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyuan</namePart>
        <namePart type="family">Mei</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>Adapter-tuning is a paradigm that transfers a pretrained language model to downstream tasks by adding and tuning a small number of new parameters. Previously proposed adapter architectures are all feed-forward neural networks. In this paper, we investigate the effectiveness of using tiny-attention—i.e., attention with extremely small per-head dimensionality—as adapters. Our tiny-attention adapter learns to modify the hidden states at each position directly conditioned on the hidden states at all the other positions, which is missed by the previously proposed adapters. Moreover, we view its multiple attention heads as a mixture of experts and propose to average their weights during deployment, which further reduces its inference computation cost. On the GLUE benchmark, our tiny-attention adapter outperforms the other parameter-efficient transfer learning methods as well as full fine-tuning while only updating 0.05% of the parameters. On the FewGLUE benchmark, its performance is comparable to that of GPT-3 and PET.</abstract>
    <identifier type="citekey">zhao-etal-2022-tiny</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.444</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.444/</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6626</start>
            <end>6638</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters
%A Zhao, Hongyu
%A Tan, Hao
%A Mei, Hongyuan
%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 zhao-etal-2022-tiny
%X Adapter-tuning is a paradigm that transfers a pretrained language model to downstream tasks by adding and tuning a small number of new parameters. Previously proposed adapter architectures are all feed-forward neural networks. In this paper, we investigate the effectiveness of using tiny-attention—i.e., attention with extremely small per-head dimensionality—as adapters. Our tiny-attention adapter learns to modify the hidden states at each position directly conditioned on the hidden states at all the other positions, which is missed by the previously proposed adapters. Moreover, we view its multiple attention heads as a mixture of experts and propose to average their weights during deployment, which further reduces its inference computation cost. On the GLUE benchmark, our tiny-attention adapter outperforms the other parameter-efficient transfer learning methods as well as full fine-tuning while only updating 0.05% of the parameters. On the FewGLUE benchmark, its performance is comparable to that of GPT-3 and PET.
%R 10.18653/v1/2022.emnlp-main.444
%U https://aclanthology.org/2022.emnlp-main.444/
%U https://doi.org/10.18653/v1/2022.emnlp-main.444
%P 6626-6638

Markdown (Informal)

[Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters](https://aclanthology.org/2022.emnlp-main.444/) (Zhao et al., EMNLP 2022)

• Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters (Zhao et al., EMNLP 2022)

ACL

• Hongyu Zhao, Hao Tan, and Hongyuan Mei. 2022. Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6626–6638, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.