Graphs in Machine Learning - Spring 2024 - MVA - ENS Paris-Saclay
News
First class will start on 08.01.2022 at 16h30.
You can join the first class with this link.
Adminstrivia
Time: Mondays 16:30
Place: Online (link to class sent on piazza, except for first one)
Piazza: Registration (with your school email) and online class discussion on piazza.
7 or 8 lectures and 3 recitations (TD)
Validation: grades from TD
TA: Achraf Azize
course description at MVA at ENS Paris-Saclay
MVA tags: content: #apprentissage, type: #méthodologique #théorique, validation: #td
Main topics
spectral graph theory, graph Laplacians
semi-supervised graph-based learning
manifold learning
graphs from flat data - graph as a non-parametric basis
online learning with graphs
real world graphs scalability and approximations
graph neural networks
social networks and recommender systems applications
large graph analysis, learning, and mining
vision applications (e.g., face recognition)
Important: Don't take this class ...
... if you don't have time to do reports. While 5-10% students finish their 3 assignments during the 2-hour long recitations, about 20% students find that they spend 3 times longer time doing homework reports than for other classes in the master program.
... if you expect your instructor to reply to your emails or not willing to read this webpage and other instructions. Piazza is the place for all communication.
... if you believe that extra extensions beyond the rules below would be granted or if you cannot deliver the project report on time.
Intro
Graphs come handy whenever we deal with relations between the objects. This course, focused on learning, will present methods involving two main sources of graphs in ML: 1) graphs coming from networks, e.g., social, biological, technology, etc. and 2) graphs coming from flat (often vision) data, where a graph serves as a useful nonparametric basis and is an effective data representation for such tasks as spectral clustering, manifold or semi-supervised learning. We will also discuss online decision-making on graphs, suitable for recommender systems or online advertising. Finally, we will always discuss the scalability of all approaches and learn how to address huge graphs in practice. The lectures will show not only how but mostly why things work. The students will learn relevant topics from spectral graph theory, learning theory, bandit theory, graph neural networks, necessary mathematical concepts and the concrete graph-based approaches for typical machine learning problems. The practical sessions will provide hands-on experience on interesting applications (e.g., online face recognizer) and state-of-the-art graphs processing tools.