Learning continuous representations for Knowledge Graphs / by Caglar Demir ; [Reviewers: Prof. Dr. Axel-Cyrille Ngonga Ngomo, Prof. Dr. Sören Auer, Jun.-Prof. Dr. Sebastian Peitz]. Paderborn, 2023
Content
- Contents
- I Introduction
- II Contributions
- A Physical Embedding Model for Knowledge Graphs
- A Shallow Neural Model for Relation Prediction
- Convolutional Complex Knowledge Graph Embeddings
- Convolutional Hypercomplex Embeddings for Link Prediction
- Kronecker Decomposition for Knowledge Graph Embeddings
- Polyak Parameter Ensemble for Knowledge Graph Embeddings
- Learning Permutation-Invariant Embeddings for Description Logic Concepts
- III Software Frameworks and Use cases
- DICE Embeddings Framework
- Large-scale Knowledge Graph Embeddings
- DICE Embeddings: Hardware-agnostic Framework for Large-scale Knowledge Graph Embeddings
- Downstream Applications
- Ontolearn Framework
- Use Case: Deep Reinforcement Learning for Class Expression Learning
- Use Case: Rapid Explainability For Skill Description Learning
- IV Conclusion and Future Work