@inproceedings{van-der-heijden-etal-2023-k,
title = "K-hop neighbourhood regularization for few-shot learning on graphs: A case study of text classification",
author = "van der Heijden, Niels and
Shutova, Ekaterina and
Yannakoudakis, Helen",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.85",
doi = "10.18653/v1/2023.eacl-main.85",
pages = "1187--1200",
abstract = "We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings. We introduce K-hop Neighbourhood Regularization, a regularizer for heterogeneous graphs, and show that it stabilizes and improves learning when only a few training samples are available. We furthermore propose a simplification in the graph-construction method, which results in a graph that is ∼7 times less dense and yields better performance in little-resource settings while performing on par with the state of the art in high-resource settings. Finally, we introduce a new variant of Adaptive Pseudo-Labeling tailored for word-document graphs. When using as little as 20 samples for training, we outperform a strong TextGCN baseline with 17{\%} in absolute accuracy on average over eight languages. We demonstrate that our method can be applied to document classification without any language model pretraining on a wide range of typologically diverse languages while performing on par with large pretrained language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-der-heijden-etal-2023-k">
<titleInfo>
<title>K-hop neighbourhood regularization for few-shot learning on graphs: A case study of text classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niels</namePart>
<namePart type="family">van der Heijden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings. We introduce K-hop Neighbourhood Regularization, a regularizer for heterogeneous graphs, and show that it stabilizes and improves learning when only a few training samples are available. We furthermore propose a simplification in the graph-construction method, which results in a graph that is ∼7 times less dense and yields better performance in little-resource settings while performing on par with the state of the art in high-resource settings. Finally, we introduce a new variant of Adaptive Pseudo-Labeling tailored for word-document graphs. When using as little as 20 samples for training, we outperform a strong TextGCN baseline with 17% in absolute accuracy on average over eight languages. We demonstrate that our method can be applied to document classification without any language model pretraining on a wide range of typologically diverse languages while performing on par with large pretrained language models.</abstract>
<identifier type="citekey">van-der-heijden-etal-2023-k</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.85</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.85</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1187</start>
<end>1200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T K-hop neighbourhood regularization for few-shot learning on graphs: A case study of text classification
%A van der Heijden, Niels
%A Shutova, Ekaterina
%A Yannakoudakis, Helen
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F van-der-heijden-etal-2023-k
%X We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings. We introduce K-hop Neighbourhood Regularization, a regularizer for heterogeneous graphs, and show that it stabilizes and improves learning when only a few training samples are available. We furthermore propose a simplification in the graph-construction method, which results in a graph that is ∼7 times less dense and yields better performance in little-resource settings while performing on par with the state of the art in high-resource settings. Finally, we introduce a new variant of Adaptive Pseudo-Labeling tailored for word-document graphs. When using as little as 20 samples for training, we outperform a strong TextGCN baseline with 17% in absolute accuracy on average over eight languages. We demonstrate that our method can be applied to document classification without any language model pretraining on a wide range of typologically diverse languages while performing on par with large pretrained language models.
%R 10.18653/v1/2023.eacl-main.85
%U https://aclanthology.org/2023.eacl-main.85
%U https://doi.org/10.18653/v1/2023.eacl-main.85
%P 1187-1200
Markdown (Informal)
[K-hop neighbourhood regularization for few-shot learning on graphs: A case study of text classification](https://aclanthology.org/2023.eacl-main.85) (van der Heijden et al., EACL 2023)
ACL