@inproceedings{sun-chen-2025-enhancing,
title = "Enhancing the Prototype Network with Local-to-Global Optimization for Few-Shot Relation Extraction",
author = "Sun, Hui and
Chen, Rongxin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.145/",
doi = "10.18653/v1/2025.findings-naacl.145",
pages = "2668--2677",
ISBN = "979-8-89176-195-7",
abstract = "Few-Shot Relation Extraction (FSRE) aims to achieve high classification performance by training relation classification models with a small amount of labeled data. Prototypical networks serve as a straightforward and efficient method for optimizing model performance by combining similarity evaluation and contrastive learning. However, directly integrating these methods can introduce unpredictable noise, such as information redundancy, which hinders classification performance and negatively affects embedding space learning. The technique presented in this paper applies Local-To-Global optimization to enhance prototypical networks in few-shot relation extraction. Specifically, this paper develops a local optimization strategy that indirectly optimizes the prototypes by optimizing the other information contained within the prototypes. It considers relation prototypes as global anchors and incorporates the techniques introduced in this paper, such as information alignment, local contrastive learning, and a local adaptive focal loss function, to address the issues of information redundancy. This approach enables the model to learn a unified and effective embedding space. We conduct extensive experiments on the FewRel 1.0 and FewRel 2.0 datasets to validate the effectiveness of the proposed model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-chen-2025-enhancing">
<titleInfo>
<title>Enhancing the Prototype Network with Local-to-Global Optimization for Few-Shot Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongxin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Few-Shot Relation Extraction (FSRE) aims to achieve high classification performance by training relation classification models with a small amount of labeled data. Prototypical networks serve as a straightforward and efficient method for optimizing model performance by combining similarity evaluation and contrastive learning. However, directly integrating these methods can introduce unpredictable noise, such as information redundancy, which hinders classification performance and negatively affects embedding space learning. The technique presented in this paper applies Local-To-Global optimization to enhance prototypical networks in few-shot relation extraction. Specifically, this paper develops a local optimization strategy that indirectly optimizes the prototypes by optimizing the other information contained within the prototypes. It considers relation prototypes as global anchors and incorporates the techniques introduced in this paper, such as information alignment, local contrastive learning, and a local adaptive focal loss function, to address the issues of information redundancy. This approach enables the model to learn a unified and effective embedding space. We conduct extensive experiments on the FewRel 1.0 and FewRel 2.0 datasets to validate the effectiveness of the proposed model.</abstract>
<identifier type="citekey">sun-chen-2025-enhancing</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.145</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.145/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2668</start>
<end>2677</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing the Prototype Network with Local-to-Global Optimization for Few-Shot Relation Extraction
%A Sun, Hui
%A Chen, Rongxin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F sun-chen-2025-enhancing
%X Few-Shot Relation Extraction (FSRE) aims to achieve high classification performance by training relation classification models with a small amount of labeled data. Prototypical networks serve as a straightforward and efficient method for optimizing model performance by combining similarity evaluation and contrastive learning. However, directly integrating these methods can introduce unpredictable noise, such as information redundancy, which hinders classification performance and negatively affects embedding space learning. The technique presented in this paper applies Local-To-Global optimization to enhance prototypical networks in few-shot relation extraction. Specifically, this paper develops a local optimization strategy that indirectly optimizes the prototypes by optimizing the other information contained within the prototypes. It considers relation prototypes as global anchors and incorporates the techniques introduced in this paper, such as information alignment, local contrastive learning, and a local adaptive focal loss function, to address the issues of information redundancy. This approach enables the model to learn a unified and effective embedding space. We conduct extensive experiments on the FewRel 1.0 and FewRel 2.0 datasets to validate the effectiveness of the proposed model.
%R 10.18653/v1/2025.findings-naacl.145
%U https://aclanthology.org/2025.findings-naacl.145/
%U https://doi.org/10.18653/v1/2025.findings-naacl.145
%P 2668-2677
Markdown (Informal)
[Enhancing the Prototype Network with Local-to-Global Optimization for Few-Shot Relation Extraction](https://aclanthology.org/2025.findings-naacl.145/) (Sun & Chen, Findings 2025)
ACL