2025/2026
RecSys
Type:
Mago-Lego
Delivered by:
Big Data and Information Retrieval School
Where:
Faculty of Computer Science
When:
3 module
Open to:
students of one campus
Instructors:
Alexander Tarakanov
Language:
English
ECTS credits:
3
Contact hours:
24
Course Syllabus
Abstract
This course provides a comprehensive introduction to recommender systems as a core component of modern data-driven products. The course covers classical approaches such as matrix factorization and sparse linear models, spectral and graph-based methods, and modern neural approaches including graph convolutional networks and generative recommender systems. Particular emphasis is placed on understanding the mathematical foundations, algorithmic design, and practical considerations in large-scale recommendation systems used in industry.
Learning Objectives
- The main purpose of this course is to provide students with a solid theoretical and applied understanding of recommender systems, including classical methods, modern neural architectures, and generative approaches.
Expected Learning Outcomes
- Formulate recommendation problems in terms of user–item interaction data
- Apply matrix factorization methods such as SVD for collaborative filtering
- Implement and analyze sparse linear models (SLIM, EASE)
- Understand spectral methods and their role in recommendation.
- Apply graph-based approaches including Graph Convolutional Networks.
- Understand modern generative approaches to recommendation systems.
- Evaluate recommender systems using standard ranking metrics.
- Design and analyze recommendation pipelines for real-world application
Course Contents
- Introduction to Recommender Systems
- Matrix Factorization and SVD
- Sparse Linear Models (SLIM, EASE) and Spectral Methods
- Graph-Based Recommender Systems (GCN I)
- Graph-Based Recommender Systems (GCN II)
- Generative Recommender Systems
Interim Assessment
- 2025/2026 3rd module0.4 * paper_presentation + 0.3 * homework_1 + 0.3 * homework_2
Bibliography
Recommended Core Bibliography
- Mescheder, L., Nowozin, S., & Geiger, A. (2017). Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsarx&AN=edsarx.1701.04722
Recommended Additional Bibliography
- Manouselis, N., Drachsler, H., Verbert, K., Duval, E. Recommender Systems for Learning. – Springer, 2013. – ЭБС Books 24x7.