The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks, is presented. Pre-optimized ML models are connected and better performance is obtained by re-optimizing the connected one. The selection of an ML model from several small ML model candidates for each sub-task has been performed by using the idea based on Neural Architecture Search (NAS). In this paper, Differentiable Architecture Search (DARTS) and Single Path One-Shot NAS (SPOS-NAS) are tested, where the construction of loss functions is improved to keep all ML models smoothly learning. Using DARTS and SPOS-NAS as an optimization and selection as well as the connections for multi-step machine learning systems, we find that (1) such a system can quickly and successfully select highly performant model combinations, and (2) the selected models are consistent with baseline algorithms, such as grid search, and their outputs are well controlled.
@article{arxiv.2106.02301,
title = {Event Classification with Multi-step Machine Learning},
author = {Masahiko Saito and Tomoe Kishimoto and Yuya Kaneta and Taichi Itoh and Yoshiaki Umeda and Junichi Tanaka and Yutaro Iiyama and Ryu Sawada and Koji Terashi},
journal= {arXiv preprint arXiv:2106.02301},
year = {2021}
}