Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span t...

Full description

Saved in:
Bibliographic Details
Main Authors: PANG, Guansong, HENGEL, Anton Van Den, SHEN, Chunhua, CAO, Longbing
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7055
https://ink.library.smu.edu.sg/context/sis_research/article/8058/viewcontent/3447548.3467417.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-8058
record_format dspace
spelling sg-smu-ink.sis_research-80582022-04-07T09:06:20Z Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data PANG, Guansong HENGEL, Anton Van Den SHEN, Chunhua CAO, Longbing We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the learned abnormality to novel classes of anomaly (i.e., unknown anomalies) by actively exploring possible anomalies in the unlabeled data. This is achieved by jointly optimizing the exploitation of the small labeled anomaly data and the exploration of the rare unlabeled anomalies. Extensive experiments on 48 real-world datasets show that our model significantly outperforms five state-of-the-art competing methods. 2021-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7055 info:doi/10.1145/3447548.3467417 https://ink.library.smu.edu.sg/context/sis_research/article/8058/viewcontent/3447548.3467417.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 Reinforcement Learning Neural Networks Outlier Detection Intrusion Detection Artificial Intelligence and Robotics OS and Networks
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
Reinforcement Learning
Neural Networks
Outlier Detection
Intrusion Detection
Artificial Intelligence and Robotics
OS and Networks
spellingShingle Anomaly Detection
Deep Learning
Reinforcement Learning
Neural Networks
Outlier Detection
Intrusion Detection
Artificial Intelligence and Robotics
OS and Networks
PANG, Guansong
HENGEL, Anton Van Den
SHEN, Chunhua
CAO, Longbing
Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
description We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the learned abnormality to novel classes of anomaly (i.e., unknown anomalies) by actively exploring possible anomalies in the unlabeled data. This is achieved by jointly optimizing the exploitation of the small labeled anomaly data and the exploration of the rare unlabeled anomalies. Extensive experiments on 48 real-world datasets show that our model significantly outperforms five state-of-the-art competing methods.
format text
author PANG, Guansong
HENGEL, Anton Van Den
SHEN, Chunhua
CAO, Longbing
author_facet PANG, Guansong
HENGEL, Anton Van Den
SHEN, Chunhua
CAO, Longbing
author_sort PANG, Guansong
title Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
title_short Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
title_full Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
title_fullStr Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
title_full_unstemmed Toward deep supervised anomaly detection: Reinforcement learning from partially labeled anomaly data
title_sort toward deep supervised anomaly detection: reinforcement learning from partially labeled anomaly data
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/7055
https://ink.library.smu.edu.sg/context/sis_research/article/8058/viewcontent/3447548.3467417.pdf
_version_ 1770576205460799488