ExeKGLib: Knowledge Graphs-Empowered Machine Learning Analytics

TL;DR

ExeKGLib is a Python library that leverages knowledge graphs to simplify the creation of transparent, reusable, and executable machine learning pipelines for users with minimal ML expertise.

Contribution

It introduces a novel approach using knowledge graphs to enhance the transparency and reusability of ML workflows in a user-friendly Python library.

Findings

Improves transparency of ML pipelines

Enhances reusability of ML workflows

Simplifies pipeline construction for users with minimal ML knowledge

Abstract

Many machine learning (ML) libraries are accessible online for ML practitioners. Typical ML pipelines are complex and consist of a series of steps, each of them invoking several ML libraries. In this demo paper, we present ExeKGLib, a Python library that allows users with coding skills and minimal ML knowledge to build ML pipelines. ExeKGLib relies on knowledge graphs to improve the transparency and reusability of the built ML workflows, and to ensure that they are executable. We demonstrate the usage of ExeKGLib and compare it with conventional ML code to show its benefits.