Details
| Original language | English |
|---|---|
| Title of host publication | Explainable Artificial Intelligence for the Medical Domain 2024 |
| Subtitle of host publication | Proceedings of the First Workshop on Explainable Artificial Intelligence for the Medical Domain (EXPLIMED 2024) |
| Number of pages | 23 |
| Publication status | Published - 14 Nov 2024 |
| Event | 1st Workshop on Explainable Artificial Intelligence for the Medical Domain, EXPLIMED 2024 - Santiago de Compostela, Spain Duration: 20 Oct 2024 → 20 Oct 2024 |
Publication series
| Name | CEUR workshop proceedings |
|---|---|
| Publisher | CEUR-WS |
| Volume | 3831 |
| ISSN (Print) | 1613-0073 |
Abstract
Knowledge graphs (KGs) are naturally capable of capturing the convergence of data and knowledge, thereby making them highly expressive frameworks for describing and integrating heterogeneous data in a coherent and interconnected manner. However, based on the Open World Assumption (OWA), the absence of information within KGs does not indicate falsity or non-existence; it merely reflects incompleteness. The process of inductive learning over KGs involves predicting new relationships based on existing factual statements in the KG, utilizing either numerical or symbolic learning models. Recently, Knowledge Graph Embedding (KGE) and symbolic learning have received considerable attention in various downstream tasks, including Link Prediction (LP). LP techniques employ latent vector representations of entities and their relationships in KGs to infer missing links. Furthermore, as the quantity of data generated by KGs continues to increase, the necessity for additional quality assessment and validation efforts becomes more apparent. Nevertheless, state-of-the-art KG completion approaches fail to consider the quality constraints while generating predictions, resulting in the completion of KGs with erroneous relationships. The generation of accurate data and insights is of vital importance in the context of healthcare decision-making, including the processes of diagnosis, the formulation of treatment strategies, and the implementation of preventive actions. We propose a hybrid approach, VISE, which adopts the integration of symbolic learning, constraint validation, and numerical learning techniques. VISE leverages KGE to capture implicit knowledge and represent negation in KGs, thereby enhancing the predictive performance of numerical models. Our experimental results demonstrate the effectiveness of this hybrid strategy, which combines the strengths of symbolic, numerical, and constraint validation paradigms. VISE implementation is publicly accessible on GitHub (https://github.com/SDM-TIB/VISE).
Keywords
- Explainability, Knowledge Graphs, Numerical Learning, SHACL Constraints, Symbolic Learning
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Explainable Artificial Intelligence for the Medical Domain 2024: Proceedings of the First Workshop on Explainable Artificial Intelligence for the Medical Domain (EXPLIMED 2024). 2024. (CEUR workshop proceedings; Vol. 3831).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - VISE
T2 - 1st Workshop on Explainable Artificial Intelligence for the Medical Domain, EXPLIMED 2024
AU - Purohit, Disha
AU - Chudasama, Yashrajsinh
AU - Torrente, Maria
AU - Vidal, Maria Esther
N1 - Publisher Copyright: © 2024 Copyright for this paper by its authors.
PY - 2024/11/14
Y1 - 2024/11/14
N2 - Knowledge graphs (KGs) are naturally capable of capturing the convergence of data and knowledge, thereby making them highly expressive frameworks for describing and integrating heterogeneous data in a coherent and interconnected manner. However, based on the Open World Assumption (OWA), the absence of information within KGs does not indicate falsity or non-existence; it merely reflects incompleteness. The process of inductive learning over KGs involves predicting new relationships based on existing factual statements in the KG, utilizing either numerical or symbolic learning models. Recently, Knowledge Graph Embedding (KGE) and symbolic learning have received considerable attention in various downstream tasks, including Link Prediction (LP). LP techniques employ latent vector representations of entities and their relationships in KGs to infer missing links. Furthermore, as the quantity of data generated by KGs continues to increase, the necessity for additional quality assessment and validation efforts becomes more apparent. Nevertheless, state-of-the-art KG completion approaches fail to consider the quality constraints while generating predictions, resulting in the completion of KGs with erroneous relationships. The generation of accurate data and insights is of vital importance in the context of healthcare decision-making, including the processes of diagnosis, the formulation of treatment strategies, and the implementation of preventive actions. We propose a hybrid approach, VISE, which adopts the integration of symbolic learning, constraint validation, and numerical learning techniques. VISE leverages KGE to capture implicit knowledge and represent negation in KGs, thereby enhancing the predictive performance of numerical models. Our experimental results demonstrate the effectiveness of this hybrid strategy, which combines the strengths of symbolic, numerical, and constraint validation paradigms. VISE implementation is publicly accessible on GitHub (https://github.com/SDM-TIB/VISE).
AB - Knowledge graphs (KGs) are naturally capable of capturing the convergence of data and knowledge, thereby making them highly expressive frameworks for describing and integrating heterogeneous data in a coherent and interconnected manner. However, based on the Open World Assumption (OWA), the absence of information within KGs does not indicate falsity or non-existence; it merely reflects incompleteness. The process of inductive learning over KGs involves predicting new relationships based on existing factual statements in the KG, utilizing either numerical or symbolic learning models. Recently, Knowledge Graph Embedding (KGE) and symbolic learning have received considerable attention in various downstream tasks, including Link Prediction (LP). LP techniques employ latent vector representations of entities and their relationships in KGs to infer missing links. Furthermore, as the quantity of data generated by KGs continues to increase, the necessity for additional quality assessment and validation efforts becomes more apparent. Nevertheless, state-of-the-art KG completion approaches fail to consider the quality constraints while generating predictions, resulting in the completion of KGs with erroneous relationships. The generation of accurate data and insights is of vital importance in the context of healthcare decision-making, including the processes of diagnosis, the formulation of treatment strategies, and the implementation of preventive actions. We propose a hybrid approach, VISE, which adopts the integration of symbolic learning, constraint validation, and numerical learning techniques. VISE leverages KGE to capture implicit knowledge and represent negation in KGs, thereby enhancing the predictive performance of numerical models. Our experimental results demonstrate the effectiveness of this hybrid strategy, which combines the strengths of symbolic, numerical, and constraint validation paradigms. VISE implementation is publicly accessible on GitHub (https://github.com/SDM-TIB/VISE).
KW - Explainability
KW - Knowledge Graphs
KW - Numerical Learning
KW - SHACL Constraints
KW - Symbolic Learning
UR - http://www.scopus.com/inward/record.url?scp=85210892776&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85210892776
T3 - CEUR workshop proceedings
BT - Explainable Artificial Intelligence for the Medical Domain 2024
Y2 - 20 October 2024 through 20 October 2024
ER -