2019/08/31 by Xin He, Kaiyong Zhao, Xiaowen Chu · 3 citations
Computer Science · Mathematics · #cs.LG #cs.CV #stat.ML
paper · pdf · doi:10.1016/j.knosys.2020.106622
published as Knowledge-Based Systems, Volume 212, 5 January 2021, 106622 · automated machine learning (AutoML), published in journal of Knowledge-Based Systems
arxiv created 2021/04/16 · arxiv updated 2021/04/19
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.