Supporting Explainable AI on Semantic Constraint Validation

Download statistics - Document (COUNTER):

Gercke, Julian Alexander: Supporting Explainable AI on Semantic Constraint Validation. Hannover : Gottfried Wilhelm Leibniz Universität, Master Thesis, 2022, 126 S. DOI:

Selected time period:


Sum total of downloads: 284

There is a rising number of knowledge graphs available published through various sources. The enormous amount of linked data strives to give entities a semantic context. Using SHACL, the entities can be validated with respect to their context. On the other hand, an increasing usage of AI models in productive systems comes with a great responsibility in various areas. Predictive models like linear, logistic regression, and tree-based models, are still frequently used as they come with a simple structure, which allows for interpretability. However, explaining models includes verifying whether the model makes predictions based on human constraints or scientific facts. This work proposes to use the semantic context ofthe entities in knowledge graphs to validate predictive models with respect to user-defined constraints; therefore, providing a theoretical framework for a model-agnostic validation engine based on SHACL. In a second step, the model validation results are summarized in the case of a decision tree and visualized model-coherently. Finally, the performance of the framework is evaluated based on a Python implementation.
License of this version: CC BY 3.0 DE
Document Type: MasterThesis
Publishing status: publishedVersion
Issue Date: 2022-06-14
Appears in Collections:Fakultät für Elektrotechnik und Informatik

distribution of downloads over the selected time period:

downloads by country:

pos. country downloads
total perc.
1 image of flag of Germany Germany 125 44.01%
2 image of flag of United States United States 54 19.01%
3 image of flag of China China 16 5.63%
4 image of flag of Spain Spain 13 4.58%
5 image of flag of No geo information available No geo information available 7 2.46%
6 image of flag of Italy Italy 6 2.11%
7 image of flag of France France 6 2.11%
8 image of flag of Czech Republic Czech Republic 5 1.76%
9 image of flag of Iran, Islamic Republic of Iran, Islamic Republic of 4 1.41%
10 image of flag of Austria Austria 4 1.41%
    other countries 44 15.49%

Further download figures and rankings:


Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.

Search the repository