AI437
GRAPH BASED MACHINE LEARNING
- Course Code
- AI437
- Semester
- -
- Theory+Practice
- 3 + 0
- ECTS
- 5
| Course Type | Elective Course |
|---|---|
| Course Level | Bachelor's Degree |
| Year of Study | - |
| Semester | - |
| ECTS | 5 |
| Name of Lecturer(s) | - |
| Learning Outcomes |
At the end of this course, the students; |
| Mode of Delivery | |
| Prerequisites | No |
| Recommended Optional Programme Components | |
| Course Description | Introduction to graphs: structure, types, and properties, Graph representation: adjacency matrix, Laplacian, embeddings, Node classification, link prediction, and graph clustering, Graph traversal algorithms: BFS, DFS, shortest paths, Spectral graph theory basics, Graph kernels and similarity measures, Introduction to Graph Neural Networks (GNNs), GCN, GraphSAGE, GAT and other architectures, Dynamic graphs and temporal graph learning, Applications in recommendation systems, social networks, bioinformatics, and knowledge graphs, Tools and frameworks: NetworkX, PyTorch Geometric, DGL, Project-based learning on real-world graph datasets. |
| Course Contents | |
| Recommended or Required Reading | * Graph Representation Learning - William L. Hamilton * Graph Neural Networks: Foundations, Frontiers, and Applications - Lingfei Wu, Yu Chen, Yao Ma, Jiliang Tang |
| Planned Learning Activities and Teaching Methods | |
| Assessment Methods and Criteria | |
| Language of Instruction | - |
| Work Placement(s) | No |