<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2023-shot">
    <titleInfo>
        <title>Few-shot Classification with Hypersphere Modeling of Prototypes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ning</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulin</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ganqu</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaobin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haitao</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiyuan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengjun</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, varying from mean output embedding to covariance and distributions. However, using embeddings in space lacks expressivity and cannot capture class information robustly, while statistical complex modeling poses difficulty to metric designs. In this work, we use tensor fields (“areas”) to model classes from the geometrical perspective for few-shot learning. We present a simple and effective method, dubbed as hypersphere prototypes (HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius. Extending from points to areas, hyperspheres are much more expressive than embeddings. Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere. Following this idea, we also develop two variants of prototypes under other measurements. Extensive experiments and analysis on few-shot NLP tasks and comparison with 20+ competitive baselines demonstrate the effectiveness of our approach.</abstract>
    <identifier type="citekey">ding-etal-2023-shot</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.57</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.57</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>895</start>
            <end>917</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Few-shot Classification with Hypersphere Modeling of Prototypes
%A Ding, Ning
%A Chen, Yulin
%A Cui, Ganqu
%A Wang, Xiaobin
%A Zheng, Haitao
%A Liu, Zhiyuan
%A Xie, Pengjun
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ding-etal-2023-shot
%X Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, varying from mean output embedding to covariance and distributions. However, using embeddings in space lacks expressivity and cannot capture class information robustly, while statistical complex modeling poses difficulty to metric designs. In this work, we use tensor fields (“areas”) to model classes from the geometrical perspective for few-shot learning. We present a simple and effective method, dubbed as hypersphere prototypes (HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius. Extending from points to areas, hyperspheres are much more expressive than embeddings. Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere. Following this idea, we also develop two variants of prototypes under other measurements. Extensive experiments and analysis on few-shot NLP tasks and comparison with 20+ competitive baselines demonstrate the effectiveness of our approach.
%R 10.18653/v1/2023.findings-acl.57
%U https://aclanthology.org/2023.findings-acl.57
%U https://doi.org/10.18653/v1/2023.findings-acl.57
%P 895-917

Markdown (Informal)

[Few-shot Classification with Hypersphere Modeling of Prototypes](https://aclanthology.org/2023.findings-acl.57) (Ding et al., Findings 2023)

• Few-shot Classification with Hypersphere Modeling of Prototypes (Ding et al., Findings 2023)

ACL

• Ning Ding, Yulin Chen, Ganqu Cui, Xiaobin Wang, Haitao Zheng, Zhiyuan Liu, and Pengjun Xie. 2023. Few-shot Classification with Hypersphere Modeling of Prototypes. In Findings of the Association for Computational Linguistics: ACL 2023, pages 895–917, Toronto, Canada. Association for Computational Linguistics.