Graph Neural Networks

Graph Neural Networks

Delivery institution

Informatics
Artificaln intelgence

Instructor(s):

Guettala Walid

Start date

9 February 2026

End date

15 April 2026

Study field

CHARM priority field

Study level

Study load, ECTS

6

Short description

This course introduces the theoretical foundations, architectures, and applications of Graph Neural Networks. It covers message-passing frameworks, graph convolutional models, and advanced architectures for heterogeneous and dynamic graphs. Students will learn to design, implement, and evaluate GNNs for tasks such as node classification, link prediction, and graph-level representation learning.

Full description

The course provides a comprehensive understanding of graph-based deep learning. It begins with fundamental graph theory and network representation concepts, followed by detailed study of spectral and spatial GNN formulations. Key models, including GCN, GAT, GraphSAGE, and heterogeneous GNNs, are examined. Practical sessions involve applying GNNs using PyTorch Geometric and DGL libraries on real-world datasets. The course concludes with discussion of current research trends, scalability challenges, and interpretability in graph learning.

Learning outcomes

At the end of the course, the learner will be able to:

-explain the mathematical principles underlying graph representation learning;

-implement and train standard GNN architectures;

-evaluate model performance on graph-structured data;

-design and adapt GNN architectures for new tasks and heterogeneous graphs;

-critically analyze research papers in the GNN field.

Course requirements

Solid background in linear algebra, probability, and machine learning.

Working knowledge of Python and deep learning frameworks (preferably PyTorch).

Places available

60

Course literature (compulsory or recommended):

Recommended:

W. Hamilton, Graph Representation Learning, Morgan & Claypool, 2020.
Recommended:

Z. Wu et al., “A Comprehensive Survey on Graph Neural Networks,” IEEE Transactions on Neural Networks and Learning Systems, 2021.

T. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” ICLR, 2017.

Y. Hu et al., “Heterogeneous Graph Neural Networks for Scalable Asymmetric Traveling Salesman Problem Optimization,” Neurocomputing, 2025.

Planned educational activities and teaching methods:

Lectures on theory and model design.

Programming labs for implementation and experimentation.

Group project applying GNNs to a real dataset.

Paper discussions and student presentations on recent research.

Course code

IPM-24fmiGNNEG

Language

Assessment method

Final certification

Transcript of records

No

Assessment date

15 April 2026

Modality

Learning management System in use

ELTE Canvas (primary platform for course materials, announcements, and assignments) Supplementary tools: Google Colab and GitHub Classroom for coding exercises.

Contact hours per week for the student:

4

Specific regular weekly teaching day/time

Wednesdays, 10:00–12:00 (Lecture) Fridays, 10:00–12:00 (Lab session)

Time zone