CS-E4740: Federated Learning

Catalog description

Federated learning trains machine learning models across many devices that never share their raw data. The course builds it from a single design principle: a federated system is a graph whose nodes hold local datasets, and the algorithms — FedGD, FedAvg, FedProx, clustered federated learning — follow from applying different optimization methods to generalized total variation minimization over that graph.

The course then takes the parts that actually stop practitioners: how many training rounds buy how much accuracy, how to find which devices should learn together when you cannot see their data, how many malicious participants a protocol survives, what differential privacy costs in utility, and when an exchanged model parameter is still personal data under the GDPR and the EU AI Act.

Objectives

On completion, students can

• model federated learning applications using graphs;
• use total variation minimization as a design principle for federated learning;
• design federated learning algorithms by applying optimization methods to total variation minimization;
• analyze the computational and statistical properties of federated learning algorithms.

Lectures

Eight modules. All lectures are recorded and public on YouTube; slides are in the course repository.

1. From machine learning to federated learning
2. The FL design principle — empirical graphs, generalized total variation minimization
3. FL algorithms I — FedGD, FedAvg, convergence
4. FL algorithms II — FedProx, FedRelax
5. Federated clustering — clustered FL, federated k-means
6. Legal frameworks — the GDPR, the EU AI Act, data governance
7. Robustness and cyber-security — Byzantine attacks, data and model poisoning
8. Privacy — differential privacy, privacy attacks, secure aggregation

Live sessions

Alongside the recordings, the spring 2027 edition runs live clinics on YouTube: the recordings stay canonical, the live sessions handle what a recording cannot — questions mid-derivation, live debugging, and Q&A. They are open to everyone and are recorded.

• Ask Me Anything about Federated Learning — Wednesday 18 November 2026, 16:15 Helsinki time (14:15 UTC)
• Kickoff, GTVMin, fixed points and convergence, federated clustering (live coding), GDPR and the AI Act, and a live poisoning demonstration — March 2027

Textbook

A. Jung, Federated Learning: From Theory to Practice. Free on arXiv:2505.19183. The course also draws on Machine Learning: The Basics (Springer, 2022) for the recap in module 1.

Requirements and grading

5 ECTS, with a 10 ECTS extended version. The course is assessed on

• Weekly assignments. Python with numpy and scikit-learn, on real weather-station measurements from the Finnish Meteorological Institute.
• A project. A report and a recorded talk, with anonymous peer review.

Weights and deadlines for spring 2027 are not fixed yet; they will be announced here and in MyCourses before the course starts. The free follow-along track carries no credits, graded project or peer review — those require Aalto enrolment.

Prerequisites

Empirical risk minimization and the basics of supervised learning; gradient descent; linear algebra; Python with numpy and scikit-learn. Graph theory is developed from scratch, and no prior knowledge of distributed systems is assumed.

Intended audience

Master's and doctoral students in computer science, data science and electrical engineering, and practitioners who need to train models on data that cannot be centralized — health, industrial, mobile and public-sector data.