AutoML: A Survey of the State-of-the-Art. He, X., Zhao, K., & Chu, X. Knowledge-Based Systems, 212:106622, January, 2021. arXiv: 1908.00709![AutoML: A Survey of the State-of-the-Art [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.
@article{he_automl_2021,
title = {{AutoML}: {A} {Survey} of the {State}-of-the-{Art}},
volume = {212},
issn = {09507051},
shorttitle = {{AutoML}},
url = {http://arxiv.org/abs/1908.00709},
doi = {10.1016/j.knosys.2020.106622},
abstract = {Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.},
urldate = {2021-08-19},
journal = {Knowledge-Based Systems},
author = {He, Xin and Zhao, Kaiyong and Chu, Xiaowen},
month = jan,
year = {2021},
note = {arXiv: 1908.00709},
keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning},
pages = {106622},
}
Downloads: 0
{"_id":"bv9JMMbuKsqJpCW7H","bibbaseid":"he-zhao-chu-automlasurveyofthestateoftheart-2021","author_short":["He, X.","Zhao, K.","Chu, X."],"bibdata":{"bibtype":"article","type":"article","title":"AutoML: A Survey of the State-of-the-Art","volume":"212","issn":"09507051","shorttitle":"AutoML","url":"http://arxiv.org/abs/1908.00709","doi":"10.1016/j.knosys.2020.106622","abstract":"Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.","urldate":"2021-08-19","journal":"Knowledge-Based Systems","author":[{"propositions":[],"lastnames":["He"],"firstnames":["Xin"],"suffixes":[]},{"propositions":[],"lastnames":["Zhao"],"firstnames":["Kaiyong"],"suffixes":[]},{"propositions":[],"lastnames":["Chu"],"firstnames":["Xiaowen"],"suffixes":[]}],"month":"January","year":"2021","note":"arXiv: 1908.00709","keywords":"Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning","pages":"106622","bibtex":"@article{he_automl_2021,\n\ttitle = {{AutoML}: {A} {Survey} of the {State}-of-the-{Art}},\n\tvolume = {212},\n\tissn = {09507051},\n\tshorttitle = {{AutoML}},\n\turl = {http://arxiv.org/abs/1908.00709},\n\tdoi = {10.1016/j.knosys.2020.106622},\n\tabstract = {Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering the applications of DL to more areas. Automated machine learning (AutoML) becomes a promising solution to build a DL system without human assistance, and a growing number of researchers focus on AutoML. In this paper, we provide a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. First, we introduce AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS). We focus more on NAS, as it is currently very hot sub-topic of AutoML. We summarize the performance of the representative NAS algorithms on the CIFAR-10 and ImageNet datasets and further discuss several worthy studying directions of NAS methods: one/two-stage NAS, one-shot NAS, and joint hyperparameter and architecture optimization. Finally, we discuss some open problems of the existing AutoML methods for future research.},\n\turldate = {2021-08-19},\n\tjournal = {Knowledge-Based Systems},\n\tauthor = {He, Xin and Zhao, Kaiyong and Chu, Xiaowen},\n\tmonth = jan,\n\tyear = {2021},\n\tnote = {arXiv: 1908.00709},\n\tkeywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Statistics - Machine Learning},\n\tpages = {106622},\n}\n\n\n\n","author_short":["He, X.","Zhao, K.","Chu, X."],"key":"he_automl_2021","id":"he_automl_2021","bibbaseid":"he-zhao-chu-automlasurveyofthestateoftheart-2021","role":"author","urls":{"Paper":"http://arxiv.org/abs/1908.00709"},"keyword":["Computer Science - Computer Vision and Pattern Recognition","Computer Science - Machine Learning","Statistics - Machine Learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["SZvSgtLYdBsPSQ3NM","iwKepCrWBps7ojhDx"],"keywords":["computer science - computer vision and pattern recognition","computer science - machine learning","statistics - machine learning"],"search_terms":["automl","survey","state","art","he","zhao","chu"],"title":"AutoML: A Survey of the State-of-the-Art","year":2021}