Details
| Original language | English |
|---|---|
| Title of host publication | K-CAP '23 |
| Subtitle of host publication | Proceedings of the 12th Knowledge Capture Conference 2023 |
| Pages | 44-52 |
| Number of pages | 9 |
| Publication status | Published - 5 Dec 2023 |
| Event | 12th ACM International Conference on Knowledge Capture, K-CAP 2023 - Pensacola, United States Duration: 5 Dec 2023 → 7 Dec 2023 |
Abstract
Knowledge graphs (KGs) naturally capture the convergence of data and knowledge, making them 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. Inductive learning over KGs involves predicting new relationships based on existing statements in the KG, using either numerical or symbolic learning models. The Partial Completeness Assumption (PCA) heuristic efficiently guides inductive learning methods for Link Prediction (LP) by refining predictions about absent KG relationships. Nevertheless, numeric techniques- like KG embedding models- alone may fall short in accurately predicting missing information, particularly when it comes to capturing implicit knowledge and complex relationships. We propose a hybrid method named SPaRKLE that seamlessly integrates symbolic and numerical techniques, leveraging the PCA heuristic to capture implicit knowledge and enrich KGs. We empirically compare SPaRKLE with state-of-the-art KG embedding and symbolic models, using established benchmarks. Our experimental outcomes underscore the efficacy of this hybrid approach, as it harnesses the strengths of both paradigms. SPaRKLE is publicly available on GitHub1.
Keywords
- Inductive Learning, Knowledge Graphs, Symbolic Learning
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
K-CAP '23: Proceedings of the 12th Knowledge Capture Conference 2023. 2023. p. 44-52.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - SPaRKLE
T2 - 12th ACM International Conference on Knowledge Capture, K-CAP 2023
AU - Purohit, Disha
AU - Chudasama, Yashrajsinh
AU - Rivas, Ariam
AU - Vidal, Maria Esther
N1 - Funding Information: This work has been supported by TrustKG - Transforming Data in Trustable Insights (GA No. P99/2020) funded by the Leibniz Association and the EraMed project P4-LUCAT (GA No. 53000015).
PY - 2023/12/5
Y1 - 2023/12/5
N2 - Knowledge graphs (KGs) naturally capture the convergence of data and knowledge, making them 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. Inductive learning over KGs involves predicting new relationships based on existing statements in the KG, using either numerical or symbolic learning models. The Partial Completeness Assumption (PCA) heuristic efficiently guides inductive learning methods for Link Prediction (LP) by refining predictions about absent KG relationships. Nevertheless, numeric techniques- like KG embedding models- alone may fall short in accurately predicting missing information, particularly when it comes to capturing implicit knowledge and complex relationships. We propose a hybrid method named SPaRKLE that seamlessly integrates symbolic and numerical techniques, leveraging the PCA heuristic to capture implicit knowledge and enrich KGs. We empirically compare SPaRKLE with state-of-the-art KG embedding and symbolic models, using established benchmarks. Our experimental outcomes underscore the efficacy of this hybrid approach, as it harnesses the strengths of both paradigms. SPaRKLE is publicly available on GitHub1.
AB - Knowledge graphs (KGs) naturally capture the convergence of data and knowledge, making them 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. Inductive learning over KGs involves predicting new relationships based on existing statements in the KG, using either numerical or symbolic learning models. The Partial Completeness Assumption (PCA) heuristic efficiently guides inductive learning methods for Link Prediction (LP) by refining predictions about absent KG relationships. Nevertheless, numeric techniques- like KG embedding models- alone may fall short in accurately predicting missing information, particularly when it comes to capturing implicit knowledge and complex relationships. We propose a hybrid method named SPaRKLE that seamlessly integrates symbolic and numerical techniques, leveraging the PCA heuristic to capture implicit knowledge and enrich KGs. We empirically compare SPaRKLE with state-of-the-art KG embedding and symbolic models, using established benchmarks. Our experimental outcomes underscore the efficacy of this hybrid approach, as it harnesses the strengths of both paradigms. SPaRKLE is publicly available on GitHub1.
KW - Inductive Learning
KW - Knowledge Graphs
KW - Symbolic Learning
UR - http://www.scopus.com/inward/record.url?scp=85180366887&partnerID=8YFLogxK
U2 - 10.1145/3587259.3627547
DO - 10.1145/3587259.3627547
M3 - Conference contribution
AN - SCOPUS:85180366887
SN - 979-8-4007-0141-2
SP - 44
EP - 52
BT - K-CAP '23
Y2 - 5 December 2023 through 7 December 2023
ER -