Philipp D. Rohde
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Philipp D. Rohde has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Maria-Esther Vidal
TIB Leibniz Information Centre for Science and Technology
9 shared publications - Enrique Iglesias
L3S Research Center
5 shared publications - Ahmad Sakor
Leibniz University Hannover
3 shared publications - Disha Purohit
Leibniz University Hannover
2 shared publications - Emetis Niazmand
TIB Leibniz Information Centre for Science and Technology
2 shared publications Maria-Esther Vidal
Technische Informationsbibliothek (TIB) image/svg+xml
2 shared publications
Latest Publications
- Open Access
- 23 March 2026
- Published by TIB Open Publishing in Open Conference Proceedings
- Vol. 9
Mapping the Metadata Landscape of Energy Data Repositories
This paper empirically assesses how well energy‑relevant repositories supply the dataset‑ and column‑level metadata required by OEMetadata Schema. Records from ten catalogs are harvested, crosswalked to OEMetadata v2, normalized, and analyzed to compute dataset‑ and resource‑level coverage. Coverage is weak and uneven: provenance and contributor data appear mainly in OEP/OPSD; licenses are absent in half the portals; temporal/spatial metadata are sparse; access URLs are often missing; and column‑level data dictionaries are largely absent. We release crosswalks and a reproducible harvesting workflow, establishing a baseline for measuring and comparing interoperability across repositories.
- 23 March 2026
- Published by TIB Open Publishing in Open Conference Proceedings
- Vol. 9
Open AccessMapping the Metadata Landscape of Energy Data Repositories
This paper empirically assesses how well energy‑relevant repositories supply the dataset‑ and column‑level metadata required by OEMetadata Schema. Records from ten catalogs are harvested, crosswalked to OEMetadata v2, normalized, and analyzed to compute dataset‑ and resource‑level coverage. Coverage is weak and uneven: provenance and contributor data appear mainly in OEP/OPSD; licenses are absent in half the portals; temporal/spatial metadata are sparse; access URLs are often missing; and column‑level data dictionaries are largely absent. We release crosswalks and a reproducible harvesting workflow, establishing a baseline for measuring and comparing interoperability across repositories.
- Open Access
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 123379-123402
ConstrainTree: Enhancing Decision Trees With Semantic Constraint Validation
A growing number of knowledge graphs are being released by diverse sources. The massive volume of linked data aims to provide entities with semantic context. The entities can be validated in relation to their context using the Shapes Constraint Language (SHACL). On the other hand, the increasing usage of Artificial Intelligence (AI) models in productive systems entails a tremendous deal of responsibility in a variety of domains. Predictive models such as linear, logistic regression, and tree-based models are still widely employed because they have a basic structure that allows for explanation. Explanation of models, however, requires determining if the model generated predictions based on human constraints or scientific facts. This work proposes using the semantic context of entities in knowledge graphs to assess prediction models against user-defined constraints, thus providing a theoretical framework for a model-agnostic validation engine based on SHACL. In a subsequent phase, the model validation results are summarized and model-coherently visualized in the case of a decision tree. The performance of the proposed framework is studied in an empirical evaluation suggesting its efficiency.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 123379-123402
Open AccessConstrainTree: Enhancing Decision Trees With Semantic Constraint Validation
A growing number of knowledge graphs are being released by diverse sources. The massive volume of linked data aims to provide entities with semantic context. The entities can be validated in relation to their context using the Shapes Constraint Language (SHACL). On the other hand, the increasing usage of Artificial Intelligence (AI) models in productive systems entails a tremendous deal of responsibility in a variety of domains. Predictive models such as linear, logistic regression, and tree-based models are still widely employed because they have a basic structure that allows for explanation. Explanation of models, however, requires determining if the model generated predictions based on human constraints or scientific facts. This work proposes using the semantic context of entities in knowledge graphs to assess prediction models against user-defined constraints, thus providing a theoretical framework for a model-agnostic validation engine based on SHACL. In a subsequent phase, the model validation results are summarized and model-coherently visualized in the case of a decision tree. The performance of the proposed framework is studied in an empirical evaluation suggesting its efficiency.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1044-1047
Integrating Knowledge Graphs and Neuro-Symbolic AI: LDM Enables FAIR and Federated Research Data Management
Managing research digital objects (RDOs) in compliance with FAIR principles is crucial for ensuring accessibility, interoperability, and reusability across scientific domains. The Leibniz Data Manager (LDM) is a state-of-the-art framework that integrates Knowledge Graphs (KGs) and Neuro-Symbolic AI, combining the reasoning power of Large Language Models (LLMs) with structured metadata. LDM supports the management and enhancement of RDOs through entity linking, connecting datasets to external KGs like Wikidata and the Open Research Knowledge Graph (ORKG). Additionally, LDM offers federated query processing across KGs, enabling users to explore related papers, datasets, and resources through natural language questions. This demo showcases LDM's capabilities to explore RDOs, compare existing datasets, and extend metadata. By blending Neuro-Symbolic AI with FAIR and federated research data management, LDM offers a powerful tool for accelerating data-driven discovery in science. LDM is publicly accessible at https://service.tib.eu/ldmservice/.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1044-1047
Open AccessIntegrating Knowledge Graphs and Neuro-Symbolic AI: LDM Enables FAIR and Federated Research Data Management
Managing research digital objects (RDOs) in compliance with FAIR principles is crucial for ensuring accessibility, interoperability, and reusability across scientific domains. The Leibniz Data Manager (LDM) is a state-of-the-art framework that integrates Knowledge Graphs (KGs) and Neuro-Symbolic AI, combining the reasoning power of Large Language Models (LLMs) with structured metadata. LDM supports the management and enhancement of RDOs through entity linking, connecting datasets to external KGs like Wikidata and the Open Research Knowledge Graph (ORKG). Additionally, LDM offers federated query processing across KGs, enabling users to explore related papers, datasets, and resources through natural language questions. This demo showcases LDM's capabilities to explore RDOs, compare existing datasets, and extend metadata. By blending Neuro-Symbolic AI with FAIR and federated research data management, LDM offers a powerful tool for accelerating data-driven discovery in science. LDM is publicly accessible at https://service.tib.eu/ldmservice/.
- 29 December 2024
- Published by Springer Nature
- p. 11-23
Fragmenting Data Strategies to Scale Up the Knowledge Graph Creation
- 29 December 2024
- Published by Springer Nature
- p. 11-23
Fragmenting Data Strategies to Scale Up the Knowledge Graph Creation
- Open Access
- 11 September 2024
- Published by IOS Press
- p. 142-158
Semantically Describing Predictive Models for Interpretable Insights into Lung Cancer Relapse
Machine learning (ML) is becoming increasingly important in healthcare decision-making, requiring highly interpretable insights from predictive models. Although integrating ML models with knowledge graphs (KGs) holds promise, conveying model outcomes to domain experts remains challenging, hindering usability despite accuracy. We propose semantically describing predictive model insights to overcome communication barriers. Our pipeline predicts lung cancer relapse likelihood, providing oncologists with patient-centric explanations based on input characteristics. Consequently, domain experts gain insights into both the characteristics of classified lung cancer patients and their relevant population. These insights, along with model decisions, are semantically described in natural language to enhance understanding, particularly for interpretable models like LIME and SHAP. Our approach, SemDesLC, documents ML model pipelines into KGs, and fulfills the needs of three types of users: KG builders, analysts, and consumers. Experts’ opinions indicate that semantic descriptions are effective for elucidating relapse determinants. SemDesLC is openly accessible on GitHub, promoting transparency and collaboration in leveraging ML for healthcare decision support.
- 11 September 2024
- Published by IOS Press
- p. 142-158
Open AccessSemantically Describing Predictive Models for Interpretable Insights into Lung Cancer Relapse
Machine learning (ML) is becoming increasingly important in healthcare decision-making, requiring highly interpretable insights from predictive models. Although integrating ML models with knowledge graphs (KGs) holds promise, conveying model outcomes to domain experts remains challenging, hindering usability despite accuracy. We propose semantically describing predictive model insights to overcome communication barriers. Our pipeline predicts lung cancer relapse likelihood, providing oncologists with patient-centric explanations based on input characteristics. Consequently, domain experts gain insights into both the characteristics of classified lung cancer patients and their relevant population. These insights, along with model decisions, are semantically described in natural language to enhance understanding, particularly for interpretable models like LIME and SHAP. Our approach, SemDesLC, documents ML model pipelines into KGs, and fulfills the needs of three types of users: KG builders, analysts, and consumers. Experts’ opinions indicate that semantic descriptions are effective for elucidating relapse determinants. SemDesLC is openly accessible on GitHub, promoting transparency and collaboration in leveraging ML for healthcare decision support.
- Open Access
- 4 July 2024
- Published by Elsevier in Information Fusion
- Vol. 112
PALADIN: A process-based constraint language for data validation
- 4 July 2024
- Published by Elsevier in Information Fusion
- Vol. 112
Open AccessPALADIN: A process-based constraint language for data validation
- Open Access
- 5 January 2024
- Published by SAGE Publications in Semantic Web: – Interoperability, Usability, Applicability
- Vol. Preprint (Preprint) , 1-21
InterpretME: A tool for interpretations of machine learning models over knowledge graphs
In recent years, knowledge graphs (KGs) have been considered pyramids of interconnected data enriched with semantics for complex decision-making. The potential of KGs and the demand for interpretability of machine learning (ML) models in diverse domains (e.g., healthcare) have gained more attention. The lack of model transparency negatively impacts the understanding and, in consequence, interpretability of the predictions made by a model. Data-driven models should be empowered with the knowledge required to trace down their decisions and the transformations made to the input data to increase model transparency. In this paper, we propose InterpretME, a tool that using KGs, provides fine-grained representations of trained ML models. An ML model description includes data – (e.g., features’ definition and SHACL validation) and model-based characteristics (e.g., relevant features and interpretations of prediction probabilities and model decisions). InterpretME allows for defining a model’s features over data collected in various formats, e.g., RDF KGs, CSV, and JSON. InterpretME relies on the SHACL schema to validate integrity constraints over the input data. InterpretME traces the steps of data collection, curation, integration, and prediction; it documents the collected metadata in the InterpretME KG. InterpretME is published in GitHub11 https://github.com/SDM-TIB/InterpretME and Zenodo22 https://doi.org/10.5281/zenodo.8112628. The InterpretME framework includes a pipeline for enhancing the interpretability of ML models, the InterpretME KG, and an ontology to describe the main characteristics of trained ML models; a PyPI library of InterpretME is also provided33 https://pypi.org/project/InterpretME/. Additionally, a live code44 https://github.com/SDM-TIB/InterpretME_Demo, and a video55 https://www.youtube.com/watch?v=Bu4lROnY4xg demonstrating InterpretME in several use cases are also available.
- 5 January 2024
- Published by SAGE Publications in Semantic Web: – Interoperability, Usability, Applicability
- Vol. Preprint (Preprint) , 1-21
Open AccessInterpretME: A tool for interpretations of machine learning models over knowledge graphs
In recent years, knowledge graphs (KGs) have been considered pyramids of interconnected data enriched with semantics for complex decision-making. The potential of KGs and the demand for interpretability of machine learning (ML) models in diverse domains (e.g., healthcare) have gained more attention. The lack of model transparency negatively impacts the understanding and, in consequence, interpretability of the predictions made by a model. Data-driven models should be empowered with the knowledge required to trace down their decisions and the transformations made to the input data to increase model transparency. In this paper, we propose InterpretME, a tool that using KGs, provides fine-grained representations of trained ML models. An ML model description includes data – (e.g., features’ definition and SHACL validation) and model-based characteristics (e.g., relevant features and interpretations of prediction probabilities and model decisions). InterpretME allows for defining a model’s features over data collected in various formats, e.g., RDF KGs, CSV, and JSON. InterpretME relies on the SHACL schema to validate integrity constraints over the input data. InterpretME traces the steps of data collection, curation, integration, and prediction; it documents the collected metadata in the InterpretME KG. InterpretME is published in GitHub11 https://github.com/SDM-TIB/InterpretME and Zenodo22 https://doi.org/10.5281/zenodo.8112628. The InterpretME framework includes a pipeline for enhancing the interpretability of ML models, the InterpretME KG, and an ontology to describe the main characteristics of trained ML models; a PyPI library of InterpretME is also provided33 https://pypi.org/project/InterpretME/. Additionally, a live code44 https://github.com/SDM-TIB/InterpretME_Demo, and a video55 https://www.youtube.com/watch?v=Bu4lROnY4xg demonstrating InterpretME in several use cases are also available.
- 22 September 2023
- Published by Springer Nature
- p. 89-118
Challenges for Healthcare Data Analytics Over Knowledge Graphs
- 22 September 2023
- Published by Springer Nature
- p. 89-118
Challenges for Healthcare Data Analytics Over Knowledge Graphs
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1422-1423
Trusting Decentralised Knowledge Graphs and Web Data at the Web Conference
Knowledge Graphs have become a foundation for sharing data on the web and building intelligent services across many sectors and also within some of the most successful corporations in the world. The over centralisation of data on the web, however, has been raised as a concern by a number of prominent researchers in the field. For example, at the beginning of 2022 a €2.7B civil lawsuit was launched against Meta on the basis that it has abused its market dominance to impose unfair terms and conditions on UK users in order to exploit their personal data. Data centralisation can lead to a number of problems including: lock-in/siloing effects, lack of user control over their personal data, limited incentives and opportunities for interoperability and openness, and the resulting detrimental effects on privacy and innovation. A number of diverse approaches and technologies exist for decentralising data, such as federated querying and distributed ledgers. The main question is, though, what does decentralisation really mean for web data and Knowledge Graphs? What are the main issues and tradeoffs involved? These questions and others are addressed in this workshop.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1422-1423
Open AccessTrusting Decentralised Knowledge Graphs and Web Data at the Web Conference
Knowledge Graphs have become a foundation for sharing data on the web and building intelligent services across many sectors and also within some of the most successful corporations in the world. The over centralisation of data on the web, however, has been raised as a concern by a number of prominent researchers in the field. For example, at the beginning of 2022 a €2.7B civil lawsuit was launched against Meta on the basis that it has abused its market dominance to impose unfair terms and conditions on UK users in order to exploit their personal data. Data centralisation can lead to a number of problems including: lock-in/siloing effects, lack of user control over their personal data, limited incentives and opportunities for interoperability and openness, and the resulting detrimental effects on privacy and innovation. A number of diverse approaches and technologies exist for decentralising data, such as federated querying and distributed ledgers. The main question is, though, what does decentralisation really mean for web data and Knowledge Graphs? What are the main issues and tradeoffs involved? These questions and others are addressed in this workshop.