Toward explainable deep anomaly detection

Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many realworld applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; mo...

Full description

Saved in:
Bibliographic Details
Main Authors: PANG, Guansong, AGGARWAL, Charu
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7020
https://ink.library.smu.edu.sg/context/sis_research/article/8023/viewcontent/3447548.3470794.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8023
record_format dspace
spelling sg-smu-ink.sis_research-80232022-03-17T15:04:55Z Toward explainable deep anomaly detection PANG, Guansong AGGARWAL, Charu Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many realworld applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; most existing studies exclusively focus on the detection task only, including the recently emerging deep learning-based anomaly detection that leverages neural networks to learn expressive low-dimensional representations or anomaly scores for the detection task. Deep learning models, including deep anomaly detection models, are often constructed as black boxes, which have been criticized for the lack of explainability of their prediction results. To tackle this explainability issue, there have been numerous techniques introduced over the years, many of which can be utilized or adapted to offer highly explainable detection results. This tutorial aims to present a comprehensive review of the advances in deep learning-based anomaly detection and explanation. We first review popular state-of-the-art deep anomaly detection methods from different categories of approaches, followed by the introduction of a number of principled approaches used to provide anomaly explanation for deep detection models. Through this tutorial, we aim to promote the development in algorithms, theories and evaluation of explainable deep anomaly detection in the machine learning and data mining community. The slides and other materials of the tutorial are made publicly available at https://tinyurl.com/explainableDeepAD. 2021-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7020 info:doi/10.1145/3447548.3470794 https://ink.library.smu.edu.sg/context/sis_research/article/8023/viewcontent/3447548.3470794.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University anomaly detection deep learning anomaly explanation explainable machine learning anomaly localization outlying feature selection Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic anomaly detection
deep learning
anomaly explanation
explainable machine learning
anomaly localization
outlying feature selection
Databases and Information Systems
spellingShingle anomaly detection
deep learning
anomaly explanation
explainable machine learning
anomaly localization
outlying feature selection
Databases and Information Systems
PANG, Guansong
AGGARWAL, Charu
Toward explainable deep anomaly detection
description Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many realworld applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; most existing studies exclusively focus on the detection task only, including the recently emerging deep learning-based anomaly detection that leverages neural networks to learn expressive low-dimensional representations or anomaly scores for the detection task. Deep learning models, including deep anomaly detection models, are often constructed as black boxes, which have been criticized for the lack of explainability of their prediction results. To tackle this explainability issue, there have been numerous techniques introduced over the years, many of which can be utilized or adapted to offer highly explainable detection results. This tutorial aims to present a comprehensive review of the advances in deep learning-based anomaly detection and explanation. We first review popular state-of-the-art deep anomaly detection methods from different categories of approaches, followed by the introduction of a number of principled approaches used to provide anomaly explanation for deep detection models. Through this tutorial, we aim to promote the development in algorithms, theories and evaluation of explainable deep anomaly detection in the machine learning and data mining community. The slides and other materials of the tutorial are made publicly available at https://tinyurl.com/explainableDeepAD.
format text
author PANG, Guansong
AGGARWAL, Charu
author_facet PANG, Guansong
AGGARWAL, Charu
author_sort PANG, Guansong
title Toward explainable deep anomaly detection
title_short Toward explainable deep anomaly detection
title_full Toward explainable deep anomaly detection
title_fullStr Toward explainable deep anomaly detection
title_full_unstemmed Toward explainable deep anomaly detection
title_sort toward explainable deep anomaly detection
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/7020
https://ink.library.smu.edu.sg/context/sis_research/article/8023/viewcontent/3447548.3470794.pdf
_version_ 1770576189192142848