Machine Unlearning: Theory, Methods, and Evaluations with Hands-On Insights (ESSAI 2025)
Date: –
Venue: FIIT STU – Faculty of Informatics and Information Technologies
Ilkovičova 2, Bratislava, Slovakia
Organizers: Flavio Giobergia, Giovanni Stilo
Speakers: Flavio Giobergia, Giovanni Stilo
Course at the 3rd European Summer School on Artificial Intelligence (ESSAI 2025), June 30 – July 4, 2025.
This PhD course explored Machine Unlearning, covering its theoretical foundations, state-of-the-art techniques, evaluation metrics, and practical hands-on benchmarking to efficiently “forget” specific training data without full model retraining.
Instructors
- Flavio Giobergia (Polytechnic of Turin)
- Giovanni Stilo (Luiss University of Rome)
Topics Covered
- Theoretical foundations of machine unlearning
- State-of-the-art unlearning techniques
- Evaluation metrics and benchmarking
- Hands-on practical sessions with the ERASURE framework