Machine Learning on Graphs (Applied Mathematics)
Тип: На вибір студента
Кафедра: computational mathematics
Навчальний план
| Семестр | Кредити | Звітність |
| 10 | 4.5 | Залік |
Лекції
| Семестр | К-сть годин | Лектор | Група(и) |
| 10 | 16 | доцент Yu. A. Muzychuk | PMp-51m |
Лабораторні
| Семестр | К-сть годин | Група | Викладач(і) |
| 10 | 32 | PMp-51m | доцент Yu. A. Muzychuk, Ya. S. Harasym |
Опис курсу
The course “Machine Learning on Graphs” integrates the theoretical and practical aspects of applying machine learning methods to data structured as graphs. The course begins with fundamental concepts and algorithms of graph theory, graph-based models, and progresses to more advanced topics such as graph representation learning and graph neural networks. The curriculum further addresses node and edge classification as well as graph generation. Topics related to knowledge graphs and recommender systems are also examined. Considerable emphasis is placed on the acquisition of practical skills during laboratory sessions, in which students implement studied concepts using Python and the NetworkX, PyTorch Geometric, and Neo4J libraries.
Рекомендована література
Primary literature
- Goodfellow I. Deep Learning / Ian Goodfellow, Yoshua Bengio, Aaron Courville. – MIT Press, 2016. – WWW: http://www.deeplearningbook.org
- Hamilton W. Graph Representation Learning / William L. Hamilton. – McGill University, 2020. – WWW: https://www.cs.mcgill.ca/~wlh/grl_book/
- Labonne M. Hands-On Graph Neural Networks Using Python: Practical techniques and architectures for building powerful graph and deep learning apps with PyTorch / Maxime Labonne. – Packt Publishing, 2023. – 354p.
- Negro A. Graph-Powered Machine Learning / Alessandro Negro. – Manning, 2021. – 496p.
- Stamile C. Graph Machine Learning: Take graph data to the next level by applying machine learning techniques and algorithms / Claudio Stamile, Aldo Marzullo, Enrico Deusebio. – Packt Publishing, 2021. – 338p.
- Van Bruggen R. Learning Neo4j / Rik Van Bruggen. – Packt Publishing, 2014. – 222p.
- Fey Fast Graph Representation Learning with PyTorch Geometric / Matthias Fey, Jan Eric Lenssen, 2019. – WWW: https://arxiv.org/abs/1903.02428
Supplementary literature
- Easley D. Networks, Crowds, and Markets: Reasoning About a Highly Connected World / David Easley, Jon Kleinberg. – Cambridge University Press, 2010. – WWW: http://www.cs.cornell.edu/home/kleinber/networks-book/
- Barabasi A.-L. Network Science / Albert-Laszlo Barabasi. – WWW: http://networksciencebook.com/
- Robinson I. Graph Databases / Ian Robinson, Jim Webber, Emil Eifrem. – O’Reilly, 2015. – 220p.
- Needham M. Graph Algorithms: Practical Examples in Apache Spark and Neo4j / Mark Needham, Amy E. Hodler. – O’Reilly, 2019. – 268p.
- Gosnell D. The Practitioner’s Guide to Graph Data / Denise Gosnell, Matthias Broecheler. – O’Reilly, 2020. – 250p.
- Huyen C. Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications / Chip Huyen. – O’Reilly, 2022. – 386p.