Universität Wien

250124 VO Graph Algorithms and Machine Learning (2023S)

3.00 ECTS (2.00 SWS), SPL 25 - Mathematik
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
Register/Deregister for this course

Details

Language: English

Examination dates

Lecturers

Classes (iCal) - next class is marked with N

  • Friday 10.03. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 17.03. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 24.03. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 31.03. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 21.04. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 28.04. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 05.05. 16:00 - 17:30 Hörsaal 13 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 12.05. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 19.05. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 26.05. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 02.06. 16:00 - 17:30 Hörsaal 13 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 09.06. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 16.06. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 23.06. 15:00 - 17:30 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
  • Friday 30.06. 16:00 - 17:30 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

The course will be an introduction to graph representation learning.
It will begin with classical methods to understand graphical data for examples:
1. Random walks or graph Laplacians to understand concrete algorithms such as PageRank.
2. Graph neighborhood measures to create loss functions used in Machine Learning on graphs.

With this, we will discuss the theoretical and practical aspects of Graph Neural Networks (GNN), emphasizing exceptional cases such as Message Passing Algorithms.

Prerequisites:
Basics of ML
Stochastic and probability theory basics
Linear Algebra
Experience with Python helpful

Assessment and permitted materials

here are two possibilities to achieve a successful grade in the course:
Theoretical exams: you will be expected to demonstrate a rigorous understanding of the mathematics involved in the algorithms. OR
Submit a project (preferably in Python) implementing specific algorithms covered (details provided in class)

Minimum requirements and assessment criteria

Examination topics

Reading list

https://www.cs.mcgill.ca/~wlh/grl_book/files/GRL_Book.pdf

Association in the course directory

MAMV

Last modified: Tu 20.08.2024 00:15