We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
CosUKG: A Representation Learning Framework for Uncertain Knowledge Graphs.
- Authors
Shen, Qiuhui; Qu, Aiyan
- Abstract
Knowledge graphs have been extensively studied and applied, but most of these studies assume that the relationship facts in the knowledge graph are correct and deterministic. However, in the objective world, there inevitably exist uncertain relationship facts. The existing research lacks effective representation of such uncertain information. In this regard, we propose a novel representation learning framework called CosUKG, which is specifically designed for uncertain knowledge graphs. This framework models uncertain information by measuring the cosine similarity between transformed vectors and actual target vectors, effectively integrating uncertainty into the embedding process of the knowledge graph while preserving its structural information. Through multiple experiments on three public datasets, the superiority of the CosUKG framework in representing uncertain knowledge graphs is demonstrated. It achieves improved representation accuracy of uncertain information without increasing model complexity or weakening structural information.
- Subjects
KNOWLEDGE graphs; COSINE function; KNOWLEDGE representation (Information theory); INFORMATION measurement; ACCURACY of information
- Publication
Mathematics (2227-7390), 2024, Vol 12, Issue 10, p1419
- ISSN
2227-7390
- Publication type
Article
- DOI
10.3390/math12101419