Back to all courses

Federated learning

Individual course

Max amount of FITech students: 50

Persons without a valid study right at a Finnish university or university of applied sciences have preference to this course.

This course teaches theoretical foundations and efficient algorithms for federated learning (FL) applications. FL is an umbrella term for training machine learning models in a collaborative fashion from distributed collections of data. These collections can be modelled as a graph whose nodes represent computational units (such as a smartphone). FL techniques are privacy-friendly as they do not require to share raw data between nodes but only model parameter updates. You will learn how to formulate FL applications as a regularised empirical risk minimisation and solve it using distributed implementations of gradient descent.

Course contents

  • Multi-task learning
  • Complex networks
  • Clustering
  • Privacy-preserving machine learning
  • Large-scale machine learning
  • Python (Flask, scikit-learn)

Learning outcomes

After successfully completing this course, the student

  • can model networked data and models using concepts from graph theory.
  • can formulate FL problems as optimisation problems.
  • is familiar with distributed optimisation methods (gradient-descent, primal-dual).
  • can implement FL methods in Python.

Course material

We provide a web server for Python programming (JupyterHub). Students only need a computer with a web browser running that is connected to the internet.

Course book: A. Jung, “Machine Learning: The Basics”, Springer, Singapore, 2022.

Completion methods

Independent study, assignments, project-work and peer-grading.

Students can collect points from different activities:

  • programming assignments
  • theory questions (quizzes)
  • student project
  • oral exam (via Zoom)

More information in the Aalto University study guide.

You can get a digital badge after completing this course.

personalization; privacy protection; distributed learning; networks, machine learning ML koneoppiminen, tietosuoja, yksityisyyden suoja hajautettu oppiminen

Responsible teacher

Aalto University
Alexander Jung, Assistant professor

Further information about the course and studying

Aalto University
Kirsi Viitaharju

Contact person for applications

FITech Network University
Fanny Qvickström, Student services specialist
Start here
Start here
ICT Studies
5G technology,
AI and machine learning,
Industrial internet
Course code:
Study credits:
0 €
Course level:
Teaching period:
Application deadline:
Host university:
Aalto University
Who can apply:
Adult learner,
Degree student
Teaching method:
Teaching language:
General prerequisites:
Familiarity with the concept of sequences and their limit (Differential and Integral Calculus 1 MS-A0111 or equivalent) and the concept of a gradient and its use as a local linear approximation of functions (Diff. and Integ. Calculus 2 MS-A0211 or equivalent). Knowledge about eigenvalue decomposition of positive semi-definite matrices (Matrix Algebra MS-A0001 or equivalent).
Course suitable for:
Students with advanced Master level in machine learning or similar fields
Interested in this course? Subscribe and get updates about the course directly to your email. You can cancel subscription any time you want.