.png){kind=icon}
.png){kind=icon}
Return
No-Code ML Pipeline Development: Leveraging Knowledge Graphs and Language Models
.png){kind=icon}
PRE
AI
S
A
E
F
M
DOI：10.1007/978-3-031-99554-5_24.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Constructing machine learning (ML) pipelines is challenging for non-ML experts due to various tasks and methods. Despite several no-code tools, their ML catalogs remain difficult to navigate. To address these challenges, we present an interactive system that simplifies ML pipeline creation through a graphical user interface (GUI) powered by ExeKGLib, a knowledge graph (KG)-based ML framework. The GUI features a drag-and-drop interface, allowing users to design ML workflows visually without coding. In addition, a large language model (LLM)-powered assistant provides context-aware recommendations for selecting pipeline steps from the ExeKGLib graph. We also utilize ontologies and semantic validation to ensure logical dependencies within the pipeline, guaranteeing usability and correctness. The resulting pipelines are automatically translated into executable KGs and executed by ExeKGLib. We demonstrate the systems capabilities through a detailed walkthrough, highlighting its role in streamlining ML workflow creation and execution. This demo showcases the synergy between ontologies, KGs, and LLM-powered recommendations, democratizing ML pipeline development for both experts and non-experts.
Keywords:
Interactive ML Pipeline Construction
Executable Knowledge Graphs
Data Science Ontologies
Journal
S
IF:
0
Papers:
47
Citations:
0
Organization
Cited Papers