@inproceedings{sawhney-etal-2022-dmix,
title = "{DM}ix: Adaptive Distance-aware Interpolative Mixup",
author = "Sawhney, Ramit and
Thakkar, Megh and
Pandit, Shrey and
Soun, Ritesh and
Jin, Di and
Yang, Diyi and
Flek, Lucie",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.67",
doi = "10.18653/v1/2022.acl-short.67",
pages = "606--612",
abstract = "Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space. DMix leverages the hyperbolic space as a similarity measure among input samples for a richer encoded representation.DMix achieves state-of-the-art results on sentence classification over existing data augmentation methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. We probe the effectiveness of DMix in conjunction with various similarity measures and qualitatively analyze the different components.DMix being generalizable, can be applied to various tasks, models and modalities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawhney-etal-2022-dmix">
<titleInfo>
<title>DMix: Adaptive Distance-aware Interpolative Mixup</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Megh</namePart>
<namePart type="family">Thakkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrey</namePart>
<namePart type="family">Pandit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Soun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space. DMix leverages the hyperbolic space as a similarity measure among input samples for a richer encoded representation.DMix achieves state-of-the-art results on sentence classification over existing data augmentation methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. We probe the effectiveness of DMix in conjunction with various similarity measures and qualitatively analyze the different components.DMix being generalizable, can be applied to various tasks, models and modalities.</abstract>
<identifier type="citekey">sawhney-etal-2022-dmix</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.67</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.67</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>606</start>
<end>612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DMix: Adaptive Distance-aware Interpolative Mixup
%A Sawhney, Ramit
%A Thakkar, Megh
%A Pandit, Shrey
%A Soun, Ritesh
%A Jin, Di
%A Yang, Diyi
%A Flek, Lucie
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F sawhney-etal-2022-dmix
%X Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space. DMix leverages the hyperbolic space as a similarity measure among input samples for a richer encoded representation.DMix achieves state-of-the-art results on sentence classification over existing data augmentation methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. We probe the effectiveness of DMix in conjunction with various similarity measures and qualitatively analyze the different components.DMix being generalizable, can be applied to various tasks, models and modalities.
%R 10.18653/v1/2022.acl-short.67
%U https://aclanthology.org/2022.acl-short.67
%U https://doi.org/10.18653/v1/2022.acl-short.67
%P 606-612
Markdown (Informal)
[DMix: Adaptive Distance-aware Interpolative Mixup](https://aclanthology.org/2022.acl-short.67) (Sawhney et al., ACL 2022)
ACL
- Ramit Sawhney, Megh Thakkar, Shrey Pandit, Ritesh Soun, Di Jin, Diyi Yang, and Lucie Flek. 2022. DMix: Adaptive Distance-aware Interpolative Mixup. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 606–612, Dublin, Ireland. Association for Computational Linguistics.