CS-E4740 - Federated Learning D, Lectures, 28.2.2024-29.5.2024

Guest access
Please note! Course description is confirmed for two academic years, which means that in general, e.g. Learning outcomes, assessment methods and key content stays unchanged. However, via course syllabus, it is possible to specify or change the course execution in each realization of the course, such as how the contact sessions are organized, assessment methods weighted or materials used.

LEARNING OUTCOMES

after completing the course, students 

* know basic charecteristics of decentralized data 

* know basic machine learning models for decentralized data

* can implement simple federated learning algorithms 

* can analyze computational and statistical properties of federated learning algorithms

 

Credits: 5 - 10

Schedule: 28.02.2024 - 29.05.2024

Teacher in charge (valid for whole curriculum period):

Teacher in charge (applies in this implementation): Alex Jung

Contact information for the course (applies in this implementation): Associate Professor Alexander Jung (first dot last ...)

CEFR level (valid for whole curriculum period):

Language of instruction and studies (applies in this implementation):

Teaching language: English. Languages of study attainment: English

CONTENT, ASSESSMENT AND WORKLOAD

Content

  • valid for whole curriculum period:

    * Machine Learning Basics: Data, Model, Loss, Regulariation, Multi-task learning

    * Network Basics: Graphs and their Matrices, Community/Cluster Structure  

    * Federated Learning Models: Cooperative, Clustered, Personalized 

    * Distributed Optimization: Gradient-Based Methods, Primal-Dual Methods

    * Case Study: Building a Covid-19 detector app using federated learning 

  • applies in this implementation

    The basic variant (5 credits) of this course consists of 10 core lectures (schedule here) with corresponding coding assignments (schedule here). We test your completion of the coding assignments via quizzes (see Section Assignments). 

    You can upgrade the course to an extended variant (10 credits) by completing a student project (more info here).


Assessment Methods and Criteria

  • valid for whole curriculum period:

    Assignments; Project-Reports; Peer-Grading

Workload

  • valid for whole curriculum period:

    Independent Study; Assignments; Project-Work; Peer-Grading

DETAILS

Study Material

  • valid for whole curriculum period:

    * A. Jung, "Machine Learning: The Basic", Springer, 2022 http://mlbook.cs.aalto.fi 

    * S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, "Distributed Optimization and Statistical Learning via the Alternating Direction Method of Mulitpliers", Foundations and Trends in Machine Learning, 3(1):1–122, 2011. 

    * Y. SarcheshmehPour, Y. Tian, L. Zhang and A. Jung, “Networked Federated Multi-Task Learning”, arXiv e-prints, 2021.

    * Youtube Channel: https://www.youtube.com/channel/UC_tW4Z_GfJ2WCnKDtwMuDUA

Substitutes for Courses
Prerequisites
SDG: Sustainable Development Goals

    1 No Poverty

    2 Zero Hunger

    3 Good Health and Well-being

    4 Quality Education

    5 Gender Equality

    6 Clean Water and Sanitation

    7 Affordable and Clean Energy

    8 Decent Work and Economic Growth

    9 Industry, Innovation and Infrastructure

    10 Reduced Inequality

    11 Sustainable Cities and Communities

    12 Responsible Production and Consumption

    13 Climate Action

    14 Life Below Water

    15 Life on Land

    16 Peace and Justice Strong Institutions

    17 Partnerships for the Goals

FURTHER INFORMATION

Further Information

  • valid for whole curriculum period:

    Teaching Language : English

    Teaching Period : 2022-2023 Spring IV - V
    2023-2024 Spring IV - V

Rules of Conduct - Students´ Rights and Responsibilities (in force from 1 August 2020)

Aalto University Code of Academic Integrity and Handling Violations Thereof