@inproceedings{lei-etal-2022-adaptive,
title = "Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification",
author = "Lei, Tianyi and
Hu, Honghui and
Luo, Qiaoyang and
Peng, Dezhong and
Wang, Xu",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.431",
pages = "4873--4882",
abstract = "Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distinction between useful and useless task features, these methods suffer from the overfitting issue. To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task. Specifically, the proposed AMGS alleviates the overfitting based on two aspects: (i) acquiring the potential semantic representation of samples and improving model generalization through the self-supervised auxiliary task in the inner loop, (ii) leveraging the adaptive meta-learner via gradient similarity to add constraints on the gradient obtained by base-learner in the outer loop. Moreover, we make a systematic analysis of the influence of regularization on the entire framework. Experimental results on several benchmarks demonstrate that the proposed AMGS consistently improves few-shot text classification performance compared with the state-of-the-art optimization-based meta-learning approaches. The code is available at: \url{https://github.com/Tianyi-Lei}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lei-etal-2022-adaptive">
<titleInfo>
<title>Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Honghui</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaoyang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dezhong</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distinction between useful and useless task features, these methods suffer from the overfitting issue. To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task. Specifically, the proposed AMGS alleviates the overfitting based on two aspects: (i) acquiring the potential semantic representation of samples and improving model generalization through the self-supervised auxiliary task in the inner loop, (ii) leveraging the adaptive meta-learner via gradient similarity to add constraints on the gradient obtained by base-learner in the outer loop. Moreover, we make a systematic analysis of the influence of regularization on the entire framework. Experimental results on several benchmarks demonstrate that the proposed AMGS consistently improves few-shot text classification performance compared with the state-of-the-art optimization-based meta-learning approaches. The code is available at: https://github.com/Tianyi-Lei.</abstract>
<identifier type="citekey">lei-etal-2022-adaptive</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.431</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4873</start>
<end>4882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification
%A Lei, Tianyi
%A Hu, Honghui
%A Luo, Qiaoyang
%A Peng, Dezhong
%A Wang, Xu
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F lei-etal-2022-adaptive
%X Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distinction between useful and useless task features, these methods suffer from the overfitting issue. To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task. Specifically, the proposed AMGS alleviates the overfitting based on two aspects: (i) acquiring the potential semantic representation of samples and improving model generalization through the self-supervised auxiliary task in the inner loop, (ii) leveraging the adaptive meta-learner via gradient similarity to add constraints on the gradient obtained by base-learner in the outer loop. Moreover, we make a systematic analysis of the influence of regularization on the entire framework. Experimental results on several benchmarks demonstrate that the proposed AMGS consistently improves few-shot text classification performance compared with the state-of-the-art optimization-based meta-learning approaches. The code is available at: https://github.com/Tianyi-Lei.
%U https://aclanthology.org/2022.coling-1.431
%P 4873-4882
Markdown (Informal)
[Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification](https://aclanthology.org/2022.coling-1.431) (Lei et al., COLING 2022)
ACL