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

2025-08-01

AI Summary

To address the challenge that domain experts—lacking machine learning (ML) expertise—struggle to construct high-quality analytical pipelines, this paper proposes a knowledge graph–based low-code ML platform. Methodologically, it encodes ML best practices, algorithmic constraints, and domain semantics into a structured, inferable knowledge graph, enabling visual pipeline orchestration and automated execution via a graphical user interface. Technically, the platform integrates the Python ecosystem, modern GUI frameworks, and a robust pipeline automation engine. Its key contribution lies in being the first to deeply embed a reasoning-capable knowledge graph into ML workflow design, thereby significantly enhancing pipeline executability, transparency, and cross-domain reusability. Empirical validation across multiple real-world scientific and engineering case studies demonstrates the platform’s effectiveness: non-ML practitioners can independently build, interpret, and reuse high-quality analytical workflows.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Engineering
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

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.

Problem

• Enables non-ML experts to build ML pipelines easily
• Improves transparency and reusability of ML workflows
• Uses knowledge graphs to simplify ML pipeline creation

Innovation

• Python library with GUI for ML pipelines
• Knowledge graphs simplify ML for non-experts
• Enhances workflow transparency and reusability