NIE-PML Personalized Machine Learning
Go to course navigation

Main Page

Personalized machine learning (PML) is a sub-field of machine learning that aims to create models and predictions based on the unique characteristics and behaviors of individual entities. While PML is commonly used in applications such as recommender systems, which recommend items to users based on their personal interests, its principles can be applied to a wide range of other fields, including education, medicine, and chemical engineering. In this course, we will explore the latest PML methods from theoretical, algorithmic, and practical perspectives. Specifically, we will focus on cutting-edge models that are of interest to both the research and commercial communities. This course is designed for students seeking an advanced understanding of personalized machine learning methods and a practical introduction to applied and/or fundamental research in the field. The course is also suitable for those seeking an initial foray into research. By the conclusion of the course, students are expected to have developed a thorough understanding of personalized machine learning models and the practical skills and knowledge necessary for developing such models in research and commercial contexts. Moreover, it is expected that the course project should yield to a scientific paper (without the need of submission) or a practical solution that can be publicly shared and added to the student’s portfolio.

Lectures

WeekDateTopicMaterials
124.09.2024Intro & Organization / PML ConceptsSlides
201.10.2024Matrix Factorization MethodsSlides / Materials
308.10.2024Autoencoders for Collaborative FilteringSlides
415.10.2024RecSys (No Lecture)-
522.10.2024Similarity-based MethodsSlides / Materials
629.10.2024Deep Learning Methods for PersonalizationSlides
705.11.2024Evaluation of PMLSlides
812.11.2024Invariant ModelsSlides
919.11.2024New trends in PMLSlides
1026.11.2024Ethics in PMLSlides / Paper
1103.12.2024Practical Aspects (Guest Lecturer)N/A
1210.12.2024Temporal Dynamics and PopularitySlides
1317.12.2024Project PresentationN/A

Tutorials

WeekDateTopicMaterials
124.09.2024Introductory tutorial (Virtual)Materials - 2023
201.10.2024Matrix Factorization X AutoencodersMaterials
415.10.2024RecSys (No Lecture)-
629.10.2024Cold-start recommendationMaterials
812.11.2024Invariant ModelsMaterials
1026.11.2024Project TutorialN/A
1210.12.2024EM-Algorithm for temporal dynamicsMaterials