AutoML: A systematic review on automated machine learning with neural architecture search

AutoML (Automated Machine Learning) is an emerging field that aims to automate the process of building machine learning models. AutoML emerged to increase productivity and efficiency by automating as much as possible the inefficient work that occurs while repeating this process whenever machine lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Imrus Salehin, Md. Shamiul Islam, Pritom Saha, S.M. Noman, Azra Tuni, Md. Mehedi Hasan, Md. Abu Baten
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2024-01-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715923000604
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850055608424726528
author Imrus Salehin
Md. Shamiul Islam
Pritom Saha
S.M. Noman
Azra Tuni
Md. Mehedi Hasan
Md. Abu Baten
author_facet Imrus Salehin
Md. Shamiul Islam
Pritom Saha
S.M. Noman
Azra Tuni
Md. Mehedi Hasan
Md. Abu Baten
author_sort Imrus Salehin
collection DOAJ
description AutoML (Automated Machine Learning) is an emerging field that aims to automate the process of building machine learning models. AutoML emerged to increase productivity and efficiency by automating as much as possible the inefficient work that occurs while repeating this process whenever machine learning is applied. In particular, research has been conducted for a long time on technologies that can effectively develop high-quality models by minimizing the intervention of model developers in the process from data preprocessing to algorithm selection and tuning. In this semantic review research, we summarize the data processing requirements for AutoML approaches and provide a detailed explanation. We place greater emphasis on neural architecture search (NAS) as it currently represents a highly popular sub-topic within the field of AutoML. NAS methods use machine learning algorithms to search through a large space of possible architectures and find the one that performs best on a given task. We provide a summary of the performance achieved by representative NAS algorithms on the CIFAR-10, CIFAR-100, ImageNet and well-known benchmark datasets. Additionally, we delve into several noteworthy research directions in NAS methods including one/two-stage NAS, one-shot NAS and joint hyperparameter with architecture optimization. We discussed how the search space size and complexity in NAS can vary depending on the specific problem being addressed. To conclude, we examine several open problems (SOTA problems) within current AutoML methods that assure further investigation in future research.
format Article
id doaj-art-9c5bb41461234d7384e44e731de2e541
institution DOAJ
issn 2949-7159
language English
publishDate 2024-01-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-9c5bb41461234d7384e44e731de2e5412025-08-20T02:51:56ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592024-01-0121528110.1016/j.jiixd.2023.10.002AutoML: A systematic review on automated machine learning with neural architecture searchImrus Salehin0Md. Shamiul Islam1Pritom Saha2S.M. Noman3Azra Tuni4Md. Mehedi Hasan5Md. Abu Baten6Department of Computer Engineering, Dongseo University, 47 Jurye-ro, Sasang-gu, Busan 47011, Republic of Korea; Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; Corresponding author.Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka 1216, BangladeshDepartment of Computer Science and Engineering, Daffodil International University, Dhaka 1216, BangladeshDepartment of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh; Faculty of Computer Science and Engineering, Frankfurt University of Applied Sciences, Frankfurt 60318, GermanyDepartment of Computer Science and Engineering, University of Asia Pacific, Dhaka 1205, BangladeshDepartment of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka 1208, BangladeshDepartment of Computer Science and Engineering, Northern University Bangladesh, Dhaka 1215, BangladeshAutoML (Automated Machine Learning) is an emerging field that aims to automate the process of building machine learning models. AutoML emerged to increase productivity and efficiency by automating as much as possible the inefficient work that occurs while repeating this process whenever machine learning is applied. In particular, research has been conducted for a long time on technologies that can effectively develop high-quality models by minimizing the intervention of model developers in the process from data preprocessing to algorithm selection and tuning. In this semantic review research, we summarize the data processing requirements for AutoML approaches and provide a detailed explanation. We place greater emphasis on neural architecture search (NAS) as it currently represents a highly popular sub-topic within the field of AutoML. NAS methods use machine learning algorithms to search through a large space of possible architectures and find the one that performs best on a given task. We provide a summary of the performance achieved by representative NAS algorithms on the CIFAR-10, CIFAR-100, ImageNet and well-known benchmark datasets. Additionally, we delve into several noteworthy research directions in NAS methods including one/two-stage NAS, one-shot NAS and joint hyperparameter with architecture optimization. We discussed how the search space size and complexity in NAS can vary depending on the specific problem being addressed. To conclude, we examine several open problems (SOTA problems) within current AutoML methods that assure further investigation in future research.http://www.sciencedirect.com/science/article/pii/S2949715923000604AutoMLNeural architecture searchAdvance machine learningSearch spaceHyperparameter optimization
spellingShingle Imrus Salehin
Md. Shamiul Islam
Pritom Saha
S.M. Noman
Azra Tuni
Md. Mehedi Hasan
Md. Abu Baten
AutoML: A systematic review on automated machine learning with neural architecture search
Journal of Information and Intelligence
AutoML
Neural architecture search
Advance machine learning
Search space
Hyperparameter optimization
title AutoML: A systematic review on automated machine learning with neural architecture search
title_full AutoML: A systematic review on automated machine learning with neural architecture search
title_fullStr AutoML: A systematic review on automated machine learning with neural architecture search
title_full_unstemmed AutoML: A systematic review on automated machine learning with neural architecture search
title_short AutoML: A systematic review on automated machine learning with neural architecture search
title_sort automl a systematic review on automated machine learning with neural architecture search
topic AutoML
Neural architecture search
Advance machine learning
Search space
Hyperparameter optimization
url http://www.sciencedirect.com/science/article/pii/S2949715923000604
work_keys_str_mv AT imrussalehin automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT mdshamiulislam automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT pritomsaha automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT smnoman automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT azratuni automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT mdmehedihasan automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch
AT mdabubaten automlasystematicreviewonautomatedmachinelearningwithneuralarchitecturesearch