Geometric Relational Embeddings
–arXiv.org Artificial Intelligence
Relational representation learning transforms relational data into continuous and low-dimensional vector representations. However, vector-based representations fall short in capturing crucial properties of relational data that are complex and symbolic. We propose geometric relational embeddings, a paradigm of relational embeddings that respect the underlying symbolic structures. Specifically, this dissertation introduces various geometric relational embedding models capable of capturing: 1) complex structured patterns like hierarchies and cycles in networks and knowledge graphs; 2) logical structures in ontologies and logical constraints applicable for constraining machine learning model outputs; and 3) high-order structures between entities and relations. Our results obtained from benchmark and real-world datasets demonstrate the efficacy of geometric relational embeddings in adeptly capturing these discrete, symbolic, and structured properties inherent in relational data.
arXiv.org Artificial Intelligence
Sep-18-2024
- Country:
- Asia (0.93)
- Europe (1.00)
- North America
- Canada (0.67)
- United States > California
- Los Angeles County > Long Beach (0.13)
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Technology:
- Information Technology
- Artificial Intelligence
- Cognitive Science > Problem Solving (0.92)
- Machine Learning
- Neural Networks > Deep Learning (0.67)
- Statistical Learning (1.00)
- Natural Language (1.00)
- Representation & Reasoning
- Constraint-Based Reasoning (0.87)
- Description Logic (0.92)
- Expert Systems (0.93)
- Ontologies (1.00)
- Semantic Networks (1.00)
- Communications > Social Media (1.00)
- Data Science > Data Mining (1.00)
- Knowledge Management > Knowledge Engineering (1.00)
- Artificial Intelligence
- Information Technology