Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice

TL;DR

This paper introduces a conceptual framework outlining six key challenges faced by domain experts in developing machine learning workflows, analyzes current tools and practices, and suggests research directions to improve automation and best practices dissemination.

Contribution

It presents a novel conceptual framework for understanding challenges in domain-specific machine learning workflows and evaluates existing tools and practices against this framework.

Findings

Six key challenges identified in transforming domain problems into ML workflows

Current tools partially address these challenges, leaving some gaps

Recommendations for increasing automation and knowledge sharing in ML workflows

Abstract

Domain experts are increasingly employing machine learning to solve their domain-specific problems. This article presents six key challenges that a domain expert faces in transforming their problem into a computational workflow, and then into an executable implementation. These challenges arise out of our conceptual framework which presents the "route" of options that a domain expert may choose to take while developing their solution. To ground our conceptual framework in the state-of-the-practice, this article discusses a selection of available textual and graphical workflow systems and their support for these six challenges. Case studies from the literature in various domains are also examined to highlight the tools used by the domain experts as well as a classification of the domain-specificity and machine learning usage of their problem, workflow, and implementation. The state-of-the-practice informs our discussion of the six key challenges, where we identify which challenges are not sufficiently addressed by available tools. We also suggest possible research directions for software engineering researchers to increase the automation of these tools and disseminate best-practice techniques between software engineering and various scientific domains.