You're currently viewing an old version of this dataset. To see the current version, click here.

VISE: Validated and Invalidated Symbolic Explanations for Knowledge Graph Integrity

VISE represents a novel hybrid strategy that integrates symbolic learning, constraint validation, and numerical learning approaches. VISE employs KGE to capture implicit information and represent negation in KGs, thereby enhancing the prediction performance of numerical models. The experimental results demonstrate the efficacy of this hybrid technique, which effectively integrates the strengths of symbolic, numerical, and constraint validation paradigms.

Data and Resources

Cite this as

Disha Purohit, Yashrajsinh Chudasama, Maria Torrente, Maria-Esther Vidal (2024). Dataset: VISE: Validated and Invalidated Symbolic Explanations for Knowledge Graph Integrity. https://doi.org/10.57702/38jfs1vi

DOI retrieved: September 19, 2024

Additional Info

Field Value
Created September 19, 2024
Last update October 1, 2024
License cc-by: Creative Commons Attribution
Source https://github.com/SDM-TIB/VISE?tab=readme-ov-file
Author Disha Purohit
More Authors
Yashrajsinh Chudasama
Maria Torrente
Maria-Esther Vidal
Author Email Disha Purohit
Maintainer Disha Purohit
Maintainer Email Disha Purohit
Language English
Access Rights Public