@inproceedings{gulati-etal-2024-distribution,
title = "Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression",
author = "Gulati, Aryan and
Dong, Xingjian and
Hurtado, Carlos and
Shekkizhar, Sarath and
Swayamdipta, Swabha and
Ortega, Antonio",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.758/",
doi = "10.18653/v1/2024.findings-emnlp.758",
pages = "12943--12959",
abstract = "As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data are computationally complex and storage-intensive. We propose a novel soft clustering approach for OOD detection based on non-negative kernel regression. Our approach greatly reduces computational and space complexities (up to $11\times$ improvement in inference time and 87{\%} reduction in storage requirements). It outperforms existing approaches by up to 4 AUROC points on four benchmarks. We also introduce an entropy-constrained version of our algorithm, leading to further reductions in storage requirements (up to 97{\%} lower than comparable approaches) while retaining competitive performance. Our soft clustering approach for OOD detection highlights its potential for detecting tail-end phenomena in extreme-scale data settings. Our source code is available on Github."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gulati-etal-2024-distribution">
<titleInfo>
<title>Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aryan</namePart>
<namePart type="family">Gulati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingjian</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Hurtado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarath</namePart>
<namePart type="family">Shekkizhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data are computationally complex and storage-intensive. We propose a novel soft clustering approach for OOD detection based on non-negative kernel regression. Our approach greatly reduces computational and space complexities (up to 11\times improvement in inference time and 87% reduction in storage requirements). It outperforms existing approaches by up to 4 AUROC points on four benchmarks. We also introduce an entropy-constrained version of our algorithm, leading to further reductions in storage requirements (up to 97% lower than comparable approaches) while retaining competitive performance. Our soft clustering approach for OOD detection highlights its potential for detecting tail-end phenomena in extreme-scale data settings. Our source code is available on Github.</abstract>
<identifier type="citekey">gulati-etal-2024-distribution</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.758</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.758/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12943</start>
<end>12959</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression
%A Gulati, Aryan
%A Dong, Xingjian
%A Hurtado, Carlos
%A Shekkizhar, Sarath
%A Swayamdipta, Swabha
%A Ortega, Antonio
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gulati-etal-2024-distribution
%X As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data are computationally complex and storage-intensive. We propose a novel soft clustering approach for OOD detection based on non-negative kernel regression. Our approach greatly reduces computational and space complexities (up to 11\times improvement in inference time and 87% reduction in storage requirements). It outperforms existing approaches by up to 4 AUROC points on four benchmarks. We also introduce an entropy-constrained version of our algorithm, leading to further reductions in storage requirements (up to 97% lower than comparable approaches) while retaining competitive performance. Our soft clustering approach for OOD detection highlights its potential for detecting tail-end phenomena in extreme-scale data settings. Our source code is available on Github.
%R 10.18653/v1/2024.findings-emnlp.758
%U https://aclanthology.org/2024.findings-emnlp.758/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.758
%P 12943-12959
Markdown (Informal)
[Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression](https://aclanthology.org/2024.findings-emnlp.758/) (Gulati et al., Findings 2024)
ACL