Similarity-Aware Machine Unlearning

A new arXiv preprint (2608.00246v1) proposes a retain-aware localization method for machine unlearning that considers parameter importance to both forgotten and retained data, reducing collateral damage to semantically similar retained examples. Across eleven experimental settings on CIFAR-10 with ResNet18, the method consistently improves unlearning metrics while minimizing collateral damage, as measured by a new retain-similar evaluation set based on cosine similarity in the model embedding space.

arXiv:2608.00246v1 Announce Type: new Abstract: Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10 dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning.