Paper ID: 2302.00731

Faster Convergence with Lexicase Selection in Tree-based Automated Machine Learning

Nicholas Matsumoto, Anil Kumar Saini, Pedro Ribeiro, Hyunjun Choi, Alena Orlenko, Leo-Pekka Lyytikäinen, Jari O Laurikka, Terho Lehtimäki, Sandra Batista, Jason H. Moore

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.

Submitted: Feb 1, 2023