Swedish web site
Federated Learning for Wireless Communications2026VT, 6.0 credits
|
|
Course plan
No of lectures
8 lectures, including theoretical lessons and student-led presentations.
Recommended for
Each participant (or each group of students) will present one recent research paper relevant to the course themes.
The course was last given
This is the first version of the course. It has never been given.
Goals
Upon successful completion of the course, students will be able to:
* Identify the core challenges and opportunities of applying Federated Learning
(FL) in wireless and resource-constrained environments.
* Analyze the trade-offs between communication efficiency, computation load,
and model accuracy in distributed learning systems.
* Evaluate and propose novel system-level solutions for client selection,
resource allocation, and communication compression.
* (Not mandatory) Develop research-oriented projects or papers aligned with
their doctoral studies.
Prerequisites
Linear algebra
Probability Theory and Random Processes
(Optional) programming skills.
Some knowledge in optimization theory is a great plus.
Organization
The course consists of:
* Lectures covering theoretical and system-level foundations
* Student projects and presentations, including discussion of selected research
papers
Content
Machine Learning and Federated Learning Overview
FL for Wireless Communication and Communication for FL
Communication Efficiency Techniques
System Optimization and Resource Management in FL
Advanced Topics and System Implementations
Literature
[1] H. Ludwig and N. Baracaldo, “Federated Learning: A Comprehensive Overview
of Methods and Applications,” Springer, 2022.
https://link.springer.com/book/10.1007/978-3-030-96896-0?sap-outbound-id=16BFC9D016E1362FE8EBF8CE2B237EB41D020D14
[2] A. Jung, “Federated Learning: From Theory to Practice,” 2025.
https://arxiv.org/abs/2505.19183
[3] H. Brendan McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. -y. Arcas,
“Communication-Efficient Learning of Deep Networks from Decentralized Data,”
2016. https://arxiv.org/abs/1602.05629
Selected recent papers will be further provided during the course.
Lectures
Each main topic listed in the “Contents” section corresponds to one or two
lecture blocks.
The final day will be dedicated to student project presentations and
discussions.
Examination
Project-based examination.
Each student will select a specific topic related to the course, conduct an
analytical or simulation-based study, and present their findings.
Evaluation will be based on:
* Oral presentation and discussion
* Written report
Lectures on selected papers led by students will also contribute to the
evaluation.
Examiner
Eunjeong Jeong, Nikolaos Pappas
Credits
6 ECTS
Comments
Page responsible: Anne Moe
