Techniques for Automated Machine Learning

By Yi-Wei Chen, Qingquan Song, Xia Hu. 2019

66 citations recorded by the source corpus.

Automated machine learning (AutoML) aims to find optimal machine learning solutions automatically given a problem description, its task type, and datasets. It could release the burden of data scientists from the multifarious manual tuning process and enable the access of domain experts to the off-the-shelf machine learning solutions without extensive experience. In this paper, we portray AutoML as a bi-level optimization problem, where one problem is nested within another to search the optimum in the search space, and review the current developments of AutoML in terms of three categories, automated feature engineering (AutoFE), automated model and hyperparameter tuning (AutoMHT), and automated deep learning (AutoDL). Stateof- the-art techniques in the three categories are presented. The iterative solver is proposed to generalize AutoML techniques. We summarize popular AutoML frameworks and conclude with current open challenges of AutoML.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xia Hu
2. Qingquan Song
3. Xiao Huang
4. Kaixiong Zhou
5. Jiyan Yang
6. Hanning Zhou
7. Dehua Cheng
8. Yuandong Tian

Citations in the corpus

• Auto-GNN: Neural architecture search of graph neural networks (2019, background): “NAS is to iteratively sample the next architecture, and moves toward the optimal architecture in the search space as close as possible (Chen et al., 2021).”
• Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction (2020, background): “The rapid development of NAS research and systems has enabled the automation of state-of-the-art deep learning tools for various learning tasks in computer vision (CV) and natural language processing [6, 8].”