Enhancing data discovery with contextual pre-filtering

Javier Flores

doi:10.1186/s40537-025-01312-5

Enhancing data discovery with contextual pre-filtering

2025-11-28

0

OA

AI

DOI：10.1186/s40537-025-01312-5

Original

Original request for help

Save

Abstract

En 中文

In this paper, entity contextual pre-filtering is proposed to refine dataset relevance assessment and streamline data discovery. Heterogeneous Graph Neural Networks are used to exploit the local context embedded within graph-based schemas. The proposed pre-filtering approach is versatile and does not rely on any specific similarity metric, making it applicable to a wide range of data discovery methods. The proposed technique increases data discovery precision by reducing false positives and identifying significant data relationships. This method has been empirically validated across a variety of real-world datasets to improve data discovery efficiency and accuracy.

Keywords:

Data Discovery

Metadata Enrichment

Heterogeneous Graph Neural Networks

Enhancing data discovery with contextual pre-filtering

Abstract

Journal

Organization