<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2023-prototype">
    <titleInfo>
        <title>Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhaofeng</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters. Despite the success, most existing methods independently adapt to each task without considering knowledge transfer between tasks and are limited to low-data regimes. To overcome this issue, we propose Prototype-based HyperAdapter (PHA), a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and a prototypical hypernetwork to generate the conditional modules in a sample-efficient manner. This leads to comparable performance improvements against existing PEFT methods on multi-task learning and few-shot transfer learning. More importantly, when the available data size gets smaller, our method outperforms other strong baselines by a large margin. Based on our extensive empirical experiments across various datasets, we demonstrate that PHA strikes a better trade-off between trainable parameters, accuracy on stream tasks, and sample efficiency. Our code is publicly available at https://github.com/Bumble666/PHA</abstract>
    <identifier type="citekey">zhao-etal-2023-prototype</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.280</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.280</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>4603</start>
            <end>4615</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning
%A Zhao, Hao
%A Fu, Jie
%A He, Zhaofeng
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhao-etal-2023-prototype
%X Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters. Despite the success, most existing methods independently adapt to each task without considering knowledge transfer between tasks and are limited to low-data regimes. To overcome this issue, we propose Prototype-based HyperAdapter (PHA), a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and a prototypical hypernetwork to generate the conditional modules in a sample-efficient manner. This leads to comparable performance improvements against existing PEFT methods on multi-task learning and few-shot transfer learning. More importantly, when the available data size gets smaller, our method outperforms other strong baselines by a large margin. Based on our extensive empirical experiments across various datasets, we demonstrate that PHA strikes a better trade-off between trainable parameters, accuracy on stream tasks, and sample efficiency. Our code is publicly available at https://github.com/Bumble666/PHA
%R 10.18653/v1/2023.emnlp-main.280
%U https://aclanthology.org/2023.emnlp-main.280
%U https://doi.org/10.18653/v1/2023.emnlp-main.280
%P 4603-4615

Markdown (Informal)

[Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning](https://aclanthology.org/2023.emnlp-main.280) (Zhao et al., EMNLP 2023)

• Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning (Zhao et al., EMNLP 2023)

ACL

• Hao Zhao, Jie Fu, and Zhaofeng He. 2023. Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4603–4615, Singapore. Association for Computational Linguistics.