Enhancing Interpretability of Machine Learning Models over Knowledge Graphs

verfasst von

Yashrajsinh Chudasama, Disha Purohit, Philipp D. Rohde, Maria Esther Vidal

Abstract

Artificial Intelligence (AI) plays a critical role in data-driven decision-making frameworks. However, the lack of transparency in some machine learning (ML) models hampers their trustworthiness, especially in domains like healthcare. This demonstration aims to showcase the potential of Semantic Web technologies in enhancing the interpretability of AI. By incorporating an interpretability layer, ML models can become more reliable, providing decision-makers with deeper insights into the model’s decision-making process. InterpretME effectively documents the execution of an ML pipeline using factual statements within the InterpretME knowledge graph (KG). Consequently, crucial metadata such as hyperparameters, decision trees, and local ML interpretations are presented in both human- and machine-readable formats, facilitating symbolic reasoning on a model’s outcomes. Following the Linked Data principles, InterpretME establishes connections between entities in the InterpretME KG and their counterparts in existing KGs, thus, enhancing contextual information of the InterpretME KG entities.

Organisationseinheit(en)

Forschungszentrum L3S
Institut für Data Science

Externe Organisation(en)

Technische Informationsbibliothek (TIB) Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek

Typ

Aufsatz in Konferenzband

Anzahl der Seiten

5

Publikationsdatum

2023

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Informatik (insg.)

Ziele für nachhaltige Entwicklung

SDG 3 – Gute Gesundheit und Wohlergehen

Elektronische Version(en)

https://doi.org/https://ceur-ws.org/Vol-3526/paper-05.pdf (Zugang: Offen)