Event Classification with Multi-step Machine Learning

TL;DR

This paper explores multi-step machine learning systems that organize tasks into sub-tasks, using neural architecture search methods like DARTS and SPOS-NAS to optimize model selection and connections for improved performance.

Contribution

It demonstrates how differentiable architecture search can effectively optimize multi-step ML systems, enhancing model selection and system performance.

Findings

Multi-step ML systems can quickly select high-performing model combinations.

The selected models align with baseline algorithms like grid search.

Outputs of the system are well controlled and consistent.

Abstract

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.