LFU:online

The outcome of the course is to get familiar with imprtant graph data properties and algorithms over them and apply embedding and machine learning methods to make predictions on them. They will also get familiar with knowledge graphs and some reasoning methods over them.

The course includes the following topics:

• Introduction to applications of graphs
• Graph types and representations
• Graph properties including node, edge and graph features
• Introduction to spectral graph theory
• Node embedding methods
• Graph neural networks including GCN, GAT, MPNN and GraphSAGE
• Knowledge graphs (KG) concepts and embedding
• KG completion and reasoning

• Graph embedding methods
  • Encoder-decoder
  • DeepWalk
  • Nod2vec
• Machine learning algorithms including graph neural networks (GNNs) for predictions on graphs including
  • node prediction
  • edge prediction
  • graph prediction
• Different GNN models
  • GCN
  • GAT
  • MPNN
  • GraphSage
• Knowledge graph reasoning methods
  • rule based
  • GNN based
  • path based

Grading includes completion of the following activities

• Exercises
• Midterm exam
• Final exam

Books

• Graph Representation Learning by William L. Hamilton
• Graph Machine Learning by Claudio Stamile et. al.

Machine Learning, Statistics, Probability, Programming

Allocation of places in courses with a limited number of participants (PS, SE, VU, PJ)

In courses with a limited number of participants, course places are allocated as follows:

1. Students for whom the study duration would be extended due to the postponement are to be given priority.

2. If the criteria in no. 1 do not suffice, first, students for whom this course is part of a compulsory module are to be given priority, and second, students for whom this course is part of an elective module.

3. If the criteria in no. 1 and 2 do not suffice, the available places are drawn by random.

Curriculum BA Computer Science 2019W

Curriculum MA Computer Science 2021W