Knowledge Graph Embedding: Recent Contributions and Applications
Presenter: Amangel Bhullar
Date: February 6, 2026
Time: 12PM
Location: Lecture Space/Workshop Space, 4th Floor - 300 Ouellette Ave., School of Computer Science Advanced Computing Hub
Abstract:
Knowledge graphs (KGs) provide a structured way to represent real-world facts as relationships between enti-ties and are widely used in applications such as search engines, recommender systems, healthcare analytics, and scientific discovery. However, reasoning directly over large symbolic graphs is computationally expensive and difficult to scale. Knowledge Graph Embedding (KGE) addresses this challenge by mapping entities and rela-tions into continuous vector spaces, enabling efficient inference and prediction of missing facts.
This workshop introduces the fundamentals of knowledge graph embedding and surveys recent research contri-butions that extend traditional static models to handle hierarchical structure, temporal evolution, and scalability. In particular, the workshop discusses how modern embedding techniques incorporate geometry-aware represen-tations, temporal modeling, and graph neural networks to improve reasoning over dynamic and large-scale knowledge graphs.
Workshop Outline:
1. Introduction to Knowledge Graphs
· What is a knowledge graph?
· Examples and use cases
2. Knowledge Graph Embedding (KGE)
· Motivation for embedding symbolic graphs
· Basic embedding models
3. Recent Contributions in KGE
· Geometry-aware and hierarchical embeddings
· Temporal knowledge graph embedding
· Graph neural networks for relational reasoning
· Scalability and sparsity in large graphs
4. Applications of KGE
· Search and recommendation systems
· Question answering and information retrieval
· Biomedical and healthcare analytics
· Financial and social event modeling
· Scientific knowledge discovery
5. Challenges and Future Directions
· Handling irregular time and missing data
· Interpretability and robustness
· Open research problems
6. Conclusion and Discussion
Prerequisites:
· Basic knowledge of linear algebra and machine learning
· Familiarity with graphs and networks
· Introductory understanding of neural networks is helpful but not required
Biography:
Amangel Bhullar is a Ph.D. candidate in Computer Science at the University of Windsor, specializing in artifi-cial intelligence with a focus on knowledge representation, machine learning, and knowledge graphs. She cur-rently serves as the President of the Graduate Student Society (GSS), where she leads initiatives to enhance the academic and social experience of graduate students.
In addition to her role at GSS, Amangel is the Director of the Lancer Sport and Recreation Center (LSRC) Cor-poration and serves as a Member of the Board of Governors at the University of Windsor. Her leadership contri-butions extend further as an Ex-Officio Member of the University Senate, where she brings a student-centred perspective to university policy and governance matters.
First Offering (12PM):
Second Offering (2PM)