Open Access
PeerJ Computer Science, volume 7, pages e757
NFAD: fixing anomaly detection using normalizing flows
Publication type: Journal Article
Publication date: 2021-11-18
Journal:
PeerJ Computer Science
Quartile SCImago
Q2
Quartile WOS
Q2
Impact factor: 3.8
ISSN: 23765992
PubMed ID:
34901422
General Computer Science
Abstract
Anomaly detection is a challenging task that frequently arises in practically all areas of industry and science, from fraud detection and data quality monitoring to finding rare cases of diseases and searching for new physics. Most of the conventional approaches to anomaly detection, such as one-class SVM and Robust Auto-Encoder, are one-class classification methods, i.e., focus on separating normal data from the rest of the space. Such methods are based on the assumption of separability of normal and anomalous classes, and subsequently do not take into account any available samples of anomalies. Nonetheless, in practical settings, some anomalous samples are often available; however, usually in amounts far lower than required for a balanced classification task, and the separability assumption might not always hold. This leads to an important task—incorporating known anomalous samples into training procedures of anomaly detection models. In this work, we propose a novel model-agnostic training procedure to address this task. We reformulate one-class classification as a binary classification problem with normal data being distinguished from pseudo-anomalous samples. The pseudo-anomalous samples are drawn from low-density regions of a normalizing flow model by feeding tails of the latent distribution into the model. Such an approach allows to easily include known anomalies into the training process of an arbitrary classifier. We demonstrate that our approach shows comparable performance on one-class problems, and, most importantly, achieves comparable or superior results on tasks with variable amounts of known anomalies.
Citations by journals
|
1
|
|
|
Mathematics
|
Mathematics
1 publication, 20%
|
|
Lecture Notes in Computer Science
|
Lecture Notes in Computer Science
1 publication, 20%
|
|
Multimedia Tools and Applications
|
Multimedia Tools and Applications
1 publication, 20%
|
|
Machine Learning with Applications
|
Machine Learning with Applications
1 publication, 20%
|
|
1
|
Citations by publishers
|
1
2
|
|
|
Springer Nature
|
Springer Nature
2 publications, 40%
|
|
Multidisciplinary Digital Publishing Institute (MDPI)
|
Multidisciplinary Digital Publishing Institute (MDPI)
1 publication, 20%
|
|
Elsevier
|
Elsevier
1 publication, 20%
|
|
IEEE
|
IEEE
1 publication, 20%
|
|
1
2
|
- We do not take into account publications that without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2022,2023,2024],"ids":[0,0,0],"codes":[0,0,0],"imageUrls":["","",""],"datasets":[{"label":"Citations number","data":[1,2,2],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6"],"percentage":["20","40","40"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Mathematics","Lecture Notes in Computer Science","Multimedia Tools and Applications","Machine Learning with Applications"],"ids":[9290,1022,21526,35935],"codes":[0,0,0,0],"imageUrls":["\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp"],"datasets":[{"label":"","data":[1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[20,20,20,20],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["Springer Nature","Multidisciplinary Digital Publishing Institute (MDPI)","Elsevier","IEEE"],"ids":[8,202,17,6953],"codes":[0,0,0,0],"imageUrls":["\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/6scCJegesojp2jubwY3uKCzTAmgsaH2GIFlg6Hfk_medium.webp"],"datasets":[{"label":"","data":[2,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[40,20,20,20],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}
Metrics
Cite this
GOST |
RIS |
BibTex
Cite this
GOST
Copy
Ryzhikov A. et al. NFAD: fixing anomaly detection using normalizing flows // PeerJ Computer Science. 2021. Vol. 7. p. e757.
GOST all authors (up to 50)
Copy
Ryzhikov A., Borisyak M., Ustyuzhanin A., Derkach D. NFAD: fixing anomaly detection using normalizing flows // PeerJ Computer Science. 2021. Vol. 7. p. e757.
Cite this
RIS
Copy
TY - JOUR
DO - 10.7717/PEERJ-CS.757
UR - https://doi.org/10.7717%2FPEERJ-CS.757
TI - NFAD: fixing anomaly detection using normalizing flows
T2 - PeerJ Computer Science
AU - Ryzhikov, Artem
AU - Borisyak, Maxim
AU - Ustyuzhanin, Andrey
AU - Derkach, Denis
PY - 2021
DA - 2021/11/18 00:00:00
PB - PeerJ
SP - e757
VL - 7
PMID - 34901422
SN - 2376-5992
ER -
Cite this
BibTex
Copy
@article{2021_Ryzhikov,
author = {Artem Ryzhikov and Maxim Borisyak and Andrey Ustyuzhanin and Denis Derkach},
title = {NFAD: fixing anomaly detection using normalizing flows},
journal = {PeerJ Computer Science},
year = {2021},
volume = {7},
publisher = {PeerJ},
month = {nov},
url = {https://doi.org/10.7717%2FPEERJ-CS.757},
pages = {e757},
doi = {10.7717/PEERJ-CS.757}
}