@inproceedings{nguyen-duc-etal-2023-class,
title = "Class based Influence Functions for Error Detection",
author = "Nguyen-Duc, Thang and
Thanh-Tung, Hoang and
Tran, Quan Hung and
Huu-Tien, Dang and
Nguyen, Hieu and
T. V. Dau, Anh and
Bui, Nghi",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.104",
doi = "10.18653/v1/2023.acl-short.104",
pages = "1204--1218",
abstract = "Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information to improve the stability of IFs.Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-duc-etal-2023-class">
<titleInfo>
<title>Class based Influence Functions for Error Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Nguyen-Duc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="family">Thanh-Tung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="given">Hung</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dang</namePart>
<namePart type="family">Huu-Tien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="family">T. V. Dau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nghi</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information to improve the stability of IFs.Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost.</abstract>
<identifier type="citekey">nguyen-duc-etal-2023-class</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.104</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.104</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1204</start>
<end>1218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Class based Influence Functions for Error Detection
%A Nguyen-Duc, Thang
%A Thanh-Tung, Hoang
%A Tran, Quan Hung
%A Huu-Tien, Dang
%A Nguyen, Hieu
%A T. V. Dau, Anh
%A Bui, Nghi
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F nguyen-duc-etal-2023-class
%X Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information to improve the stability of IFs.Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost.
%R 10.18653/v1/2023.acl-short.104
%U https://aclanthology.org/2023.acl-short.104
%U https://doi.org/10.18653/v1/2023.acl-short.104
%P 1204-1218
Markdown (Informal)
[Class based Influence Functions for Error Detection](https://aclanthology.org/2023.acl-short.104) (Nguyen-Duc et al., ACL 2023)
ACL
- Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Dang Huu-Tien, Hieu Nguyen, Anh T. V. Dau, and Nghi Bui. 2023. Class based Influence Functions for Error Detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1204–1218, Toronto, Canada. Association for Computational Linguistics.