Exploring Graph Embedding in Hyperbolic Space for NLP and Semantic Web Applications

Research topic/area

Graph Embedding; NLP; Semantic Web

Type of thesis

Master

Start time

15.06.2025

Application deadline

31.12.2025

Duration of the thesis

6 Months

Description

With the development of Natural Language Processing technologies, semantic web technologies have become increasingly important in representing and organizing knowledge. These structured knowledge graphs are widely used in applications such as question answering, recommender systems, and semantic search. To help machines better understand these graphs, graph embeddings are used to map entities and relations into continuous vector spaces. This serves as a bridge between symbolic knowledge and neural models.

Most existing embedding methods use Euclidean space, which works well for flat or homogeneous graphs. However, real-world graphs, especially in semantic domains like taxonomies, ontologies, and knowledge graphs, often have hierarchical or tree-like structures. These are difficult to represent properly in Euclidean space.
This master’s thesis focuses on learning graph embedding in the Hyperbolic space. We will explore various hyperbolic graph embedding models and compare them with standard graph neural network methods like RGCN.

Your tasks:
- Learn the semantic web fundamentals (RDF, OWL, ontology structures)
- Implement and test hyperbolic spatial graph embedding methods
- Analyze the differences with RGCN embedding methods

Requirement

Requirements for students

• Interest in knowledge graphs, symbolic AI, or deep learning
• Good knowledge of at Natural Language Processing, Embedding Space, Graph Machine Learning, or Representation Learning
• Familiarity with frameworks such as PyTorch or TensorFlow

Faculty departments

• Engineering sciences
  Electrical engineering & information technologies
  Informatics
  Mechatronics & information technologies
• Natural sciences and Technology
  Mathematics

Supervision

Title, first name, last name

M.Sc Nan Liu

Organizational unit

Institut für Automation und angewandte Informatik (IAI)

Email address

nan.liu@kit.edu

Link to personal homepage/personal page

Website

Application via email

Application documents

• Curriculum vitae
• Grade transcript

E-Mail Address for application
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an nan.liu@kit.edu


Back