AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization

Unsupervised learning systems using clustering have gained significant attention for numerous applications due to their unique ability to discover patterns and structures in large unlabeled datasets. However, their effectiveness highly depends on their configuration, which requires domain-specific e...

Full description

Saved in:
Bibliographic Details
Main Authors: SHAR, Lwin Khin, GOKNIL Arda, HUSOM, Erik Johannes, SEN, Sagar Sen, YAN, Naing Tun, KIM, Kisub
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8405
https://ink.library.smu.edu.sg/context/sis_research/article/9408/viewcontent/Testing_Unsupervised_Learning___ASE_2023.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-9408
record_format dspace
spelling sg-smu-ink.sis_research-94082024-01-09T03:49:33Z AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization SHAR, Lwin Khin GOKNIL Arda, HUSOM, Erik Johannes SEN, Sagar Sen YAN, Naing Tun KIM, Kisub Unsupervised learning systems using clustering have gained significant attention for numerous applications due to their unique ability to discover patterns and structures in large unlabeled datasets. However, their effectiveness highly depends on their configuration, which requires domain-specific expertise and often involves numerous manual trials. Specifically, selecting appropriate algorithms and hyperparameters adds to the com- plexity of the configuration process. In this paper, we propose, apply, and assess an automated approach (AutoConf) for config- uring unsupervised learning systems using clustering, leveraging metamorphic testing and Bayesian optimization. Metamorphic testing is utilized to verify the configurations of unsupervised learning systems by applying a series of input transformations. We use Bayesian optimization guided by metamorphic-testing output to automatically identify the optimal configuration. The approach aims to streamline the configuration process and enhance the effectiveness of unsupervised learning systems. It has been evaluated through experiments on six datasets from three domains for anomaly detection. The evaluation results show that our approach can find configurations outperforming the baseline approaches as they achieved a recall of 0.89 and a precision of 0.84 (on average). 2023-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8405 info:doi/10.1109/ASE56229.2023.00094 https://ink.library.smu.edu.sg/context/sis_research/article/9408/viewcontent/Testing_Unsupervised_Learning___ASE_2023.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 AutoML Unsupervised learning Metamorphic Testing Bayesian Optimization Information Security Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic AutoML
Unsupervised learning
Metamorphic Testing
Bayesian Optimization
Information Security
Software Engineering
spellingShingle AutoML
Unsupervised learning
Metamorphic Testing
Bayesian Optimization
Information Security
Software Engineering
SHAR, Lwin Khin
GOKNIL Arda,
HUSOM, Erik Johannes
SEN, Sagar Sen
YAN, Naing Tun
KIM, Kisub
AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
description Unsupervised learning systems using clustering have gained significant attention for numerous applications due to their unique ability to discover patterns and structures in large unlabeled datasets. However, their effectiveness highly depends on their configuration, which requires domain-specific expertise and often involves numerous manual trials. Specifically, selecting appropriate algorithms and hyperparameters adds to the com- plexity of the configuration process. In this paper, we propose, apply, and assess an automated approach (AutoConf) for config- uring unsupervised learning systems using clustering, leveraging metamorphic testing and Bayesian optimization. Metamorphic testing is utilized to verify the configurations of unsupervised learning systems by applying a series of input transformations. We use Bayesian optimization guided by metamorphic-testing output to automatically identify the optimal configuration. The approach aims to streamline the configuration process and enhance the effectiveness of unsupervised learning systems. It has been evaluated through experiments on six datasets from three domains for anomaly detection. The evaluation results show that our approach can find configurations outperforming the baseline approaches as they achieved a recall of 0.89 and a precision of 0.84 (on average).
format text
author SHAR, Lwin Khin
GOKNIL Arda,
HUSOM, Erik Johannes
SEN, Sagar Sen
YAN, Naing Tun
KIM, Kisub
author_facet SHAR, Lwin Khin
GOKNIL Arda,
HUSOM, Erik Johannes
SEN, Sagar Sen
YAN, Naing Tun
KIM, Kisub
author_sort SHAR, Lwin Khin
title AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
title_short AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
title_full AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
title_fullStr AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
title_full_unstemmed AutoConf: Automated configuration of unsupervised learning systems using metamorphic testing and Bayesian optimization
title_sort autoconf: automated configuration of unsupervised learning systems using metamorphic testing and bayesian optimization
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8405
https://ink.library.smu.edu.sg/context/sis_research/article/9408/viewcontent/Testing_Unsupervised_Learning___ASE_2023.pdf
_version_ 1787590770170003456