pyCLAD: The universal framework for continual lifelong anomaly detection

Anomaly detection is a recognized problem with high significance and impact in many real-world settings. Continual anomaly detection is an emerging paradigm that allows for the design of anomaly detection methods capable of adapting to new challenges in dynamic environments while retaining past know...

Full description

Saved in:
Bibliographic Details
Main Authors: Kamil Faber, Bartlomiej Sniezynski, Nathalie Japkowicz, Roberto Corizzo
Format: Article
Language:English
Published: Elsevier 2025-02-01
Series:SoftwareX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352711024003649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850195160432902144
author Kamil Faber
Bartlomiej Sniezynski
Nathalie Japkowicz
Roberto Corizzo
author_facet Kamil Faber
Bartlomiej Sniezynski
Nathalie Japkowicz
Roberto Corizzo
author_sort Kamil Faber
collection DOAJ
description Anomaly detection is a recognized problem with high significance and impact in many real-world settings. Continual anomaly detection is an emerging paradigm that allows for the design of anomaly detection methods capable of adapting to new challenges in dynamic environments while retaining past knowledge. In this paper, we propose pyCLAD, the first software framework providing foundations for the design of new continual anomaly detection scenarios, strategies, and evaluation protocols, while streamlining the execution of experimental workflows with high reproducibility standards.
format Article
id doaj-art-2fecdc5cb36b49eb8048a85d75dea4ad
institution OA Journals
issn 2352-7110
language English
publishDate 2025-02-01
publisher Elsevier
record_format Article
series SoftwareX
spelling doaj-art-2fecdc5cb36b49eb8048a85d75dea4ad2025-08-20T02:13:49ZengElsevierSoftwareX2352-71102025-02-012910199410.1016/j.softx.2024.101994pyCLAD: The universal framework for continual lifelong anomaly detectionKamil Faber0Bartlomiej Sniezynski1Nathalie Japkowicz2Roberto Corizzo3AGH University of Krakow, Department of Computer Science, Adama Mickiewicza 30, Krakow, 30-059, PolandAGH University of Krakow, Department of Computer Science, Adama Mickiewicza 30, Krakow, 30-059, PolandAmerican University, Department of Computer Science, 4400 Massachusetts Ave NW, Washington, 20016, DC, United StatesAGH University of Krakow, Department of Computer Science, Adama Mickiewicza 30, Krakow, 30-059, Poland; American University, Department of Computer Science, 4400 Massachusetts Ave NW, Washington, 20016, DC, United States; Corresponding author at: American University, Department of Computer Science, 4400 Massachusetts Ave NW, Washington, 20016, DC, United States.Anomaly detection is a recognized problem with high significance and impact in many real-world settings. Continual anomaly detection is an emerging paradigm that allows for the design of anomaly detection methods capable of adapting to new challenges in dynamic environments while retaining past knowledge. In this paper, we propose pyCLAD, the first software framework providing foundations for the design of new continual anomaly detection scenarios, strategies, and evaluation protocols, while streamlining the execution of experimental workflows with high reproducibility standards.http://www.sciencedirect.com/science/article/pii/S2352711024003649Continual anomaly detectionLifelong anomaly detectionContinual learningAnomaly detectionSoftware
spellingShingle Kamil Faber
Bartlomiej Sniezynski
Nathalie Japkowicz
Roberto Corizzo
pyCLAD: The universal framework for continual lifelong anomaly detection
SoftwareX
Continual anomaly detection
Lifelong anomaly detection
Continual learning
Anomaly detection
Software
title pyCLAD: The universal framework for continual lifelong anomaly detection
title_full pyCLAD: The universal framework for continual lifelong anomaly detection
title_fullStr pyCLAD: The universal framework for continual lifelong anomaly detection
title_full_unstemmed pyCLAD: The universal framework for continual lifelong anomaly detection
title_short pyCLAD: The universal framework for continual lifelong anomaly detection
title_sort pyclad the universal framework for continual lifelong anomaly detection
topic Continual anomaly detection
Lifelong anomaly detection
Continual learning
Anomaly detection
Software
url http://www.sciencedirect.com/science/article/pii/S2352711024003649
work_keys_str_mv AT kamilfaber pycladtheuniversalframeworkforcontinuallifelonganomalydetection
AT bartlomiejsniezynski pycladtheuniversalframeworkforcontinuallifelonganomalydetection
AT nathaliejapkowicz pycladtheuniversalframeworkforcontinuallifelonganomalydetection
AT robertocorizzo pycladtheuniversalframeworkforcontinuallifelonganomalydetection