2 papers
cs.LG2026
On the importance of multiple training seeds for evaluating machine unlearning
Jamie Lanyon, Axel Finke, Petros Andreou +1
Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining. Most practical unlearning algorithms are only approximate and…
cs.CV2026
SUPREME: A Multi-GPU Framework for Reproducible Image Unlearning Method Evaluation
Petros Andreou, Jamie Lanyon, Axel Finke +1
Machine unlearning removes the influence of specific training data from a trained model without retraining it from scratch. Evaluating an unlearning method requires repeating train…