期刊
GENETIC PROGRAMMING, EUROGP 2023
卷 13986, 期 -, 页码 165-181出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-29573-7_11
关键词
Parent Selection; NSGA-II; Lexicase; Convergence; Trie
In this paper, we compare the role of two commonly used parent selection methods in evolving machine learning pipelines in TPOT. Results show that lexicase selection leads to significantly faster convergence compared to NSGA-II. We also compare the exploration of the search space by these selection methods using a trie data structure.
In many evolutionary computation systems, parent selection methods can affect, among other things, convergence to a solution. In this paper, we present a study comparing the role of two commonly used parent selection methods in evolving machine learning pipelines in an automated machine learning system called Tree-based Pipeline Optimization Tool (TPOT). Specifically, we demonstrate, using experiments on multiple datasets, that lexicase selection leads to significantly faster convergence as compared to NSGA-II in TPOT. We also compare the exploration of parts of the search space by these selection methods using a trie data structure that contains information about the pipelines explored in a particular run.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据