首页|Automated search space and search strategy selection for AutoML
Automated search space and search strategy selection for AutoML
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
Existing works on Automated Machine Learning (AutoML) are mainly based on predefined search space. This paper seeks synergetic automation of two ingredients, i.e., search space and search strategies. Specifically, we formulate the automation of search space and search strategies as a combinatorial optimization problem. Our empirical study on many architecture benchmarks shows that identifying the suitable search space exerts more effect than choosing a sophisticated search strategy. Motivated by this, we attempt to leverage a machine learning method to solve the discrete optimization problem, and thus develop a Layered Architecture Search Tree (LArST) approach to synergize these two components. In addition, we use a probe model-based method to extract dataset-wise features, i.e., meta-features, which is able to facilitate the estimation of proper search space and search strategy for a given task. Experimental results show the efficacy of our approach under different search mechanisms and various datasets and hardware platforms. (c) 2021 Elsevier Ltd. All rights reserved.
AutoMLSearch space selectionCombinatorial optimization for AutoML
NSTL
Elsevier
