ExeKGLib: A Platform for Machine Learning Analytics based on Knowledge Graphs

TL;DR

ExeKGLib is a Python platform that simplifies the creation of machine learning pipelines for non-experts by leveraging knowledge graphs to encode ML knowledge, enhancing transparency, reusability, and accessibility.

Contribution

The paper introduces ExeKGLib, a novel Python library with a graphical interface that enables non-ML experts to build and execute ML pipelines using knowledge graphs.

Findings

Improves accessibility of ML pipeline creation for non-experts.

Enhances transparency and reusability of ML workflows.

Demonstrates usability through real-world use cases.

Abstract

Nowadays machine learning (ML) practitioners have access to numerous ML libraries available online. Such libraries can be used to create ML pipelines that consist of a series of steps where each step may invoke up to several ML libraries that are used for various data-driven analytical tasks. Development of high-quality ML pipelines is non-trivial; it requires training, ML expertise, and careful development of each step. At the same time, domain experts in science and engineering may not possess such ML expertise and training while they are in pressing need of ML-based analytics. In this paper, we present our ExeKGLib, a Python library enhanced with a graphical interface layer that allows users with minimal ML knowledge to build ML pipelines. This is achieved by relying on knowledge graphs that encode ML knowledge in simple terms accessible to non-ML experts. ExeKGLib also allows improving the transparency and reusability of the built ML workflows and ensures that they are executable. We show the usability and usefulness of ExeKGLib by presenting real use cases.