Work

Git Workflow for Active Learning: A Development Methodology Proposal for Data-Centric AI Projects

Year: 2023

Type: conference-paper

Abstract: As soon as Artificial Intelligence (AI) projects grow from small feasibility studies to mature projects, developers and data scientists face new challenges, such as collaboration with other developers, versioning data, or traceability of model metrics and other resulting artifacts. This paper suggests a data-centric AI project with an Active Learning (AL) loop from a developer perspective and presents ”Git Workflow for AL”: A methodology proposal to guide teams on how to structure a project and solve implementation challenges. We introduce principles for data, code, as well as automation, and present a new branching workflow. The evaluation shows that the proposed method is an enabler for fulfilling established best practices.

Source: International Conference on Evaluation of Novel Approaches to Software Engineering

DOI: 10.5220/0011988400003464

Authors: Fabian Stieler, Bernhard Bauer

Institution: University of Augsburg

Language: English

Topic: Software Engineering Techniques and Practices

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Bundesministerium für Bildung und Forschung

Award: G2532462694