@inproceedings{reiss-etal-2024-zero,
title = "From Zero to Hero: Cold-Start Anomaly Detection",
author = "Reiss, Tal and
Kour, George and
Zwerdling, Naama and
Anaby Tavor, Ateret and
Hoshen, Yedid",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.453",
pages = "7607--7617",
abstract = "When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such {``}cold-start{''} cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored $\textit{cold-start}$ setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reiss-etal-2024-zero">
<titleInfo>
<title>From Zero to Hero: Cold-Start Anomaly Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Reiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Kour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Zwerdling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ateret</namePart>
<namePart type="family">Anaby Tavor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yedid</namePart>
<namePart type="family">Hoshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such “cold-start” cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.</abstract>
<identifier type="citekey">reiss-etal-2024-zero</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.453</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7607</start>
<end>7617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Zero to Hero: Cold-Start Anomaly Detection
%A Reiss, Tal
%A Kour, George
%A Zwerdling, Naama
%A Anaby Tavor, Ateret
%A Hoshen, Yedid
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F reiss-etal-2024-zero
%X When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such “cold-start” cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.
%U https://aclanthology.org/2024.findings-acl.453
%P 7607-7617
Markdown (Informal)
[From Zero to Hero: Cold-Start Anomaly Detection](https://aclanthology.org/2024.findings-acl.453) (Reiss et al., Findings 2024)
ACL
- Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby Tavor, and Yedid Hoshen. 2024. From Zero to Hero: Cold-Start Anomaly Detection. In Findings of the Association for Computational Linguistics ACL 2024, pages 7607–7617, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.