Loss-Free Machine Unlearning

arXiv:2402.19308v1 Announce Type: new
Abstract: We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance. This is computationally expensive and necessitates the storage of the whole dataset for the lifetime of the model. Retraining-free approaches often utilise Fisher information, which is derived from the loss and requires labelled data which may not be available. Thus, we present an extension to the …

abstract arxiv cs.cv cs.lg dataset fisher free information loss machine performance retraining storage type unlearning