Skip to content
InfoResearchPeer-reviewed

MaxDiv: Zero-Shot Machine Unlearning via Distributionally Divergent Erasing Samples

Published
Record updated
View JSON

Summary

MaxDiv is a zero-shot machine unlearning method that erases knowledge from a model without access to its original training data. It generates erasing samples by negating the distributions of the data to be forgotten, and adds knowledge distillation to prevent catastrophic forgetting of retained information. Evaluations on MNIST, SVHN, CIFAR-10, CIFAR-100 and TinyImageNet reportedly show superior performance over current state-of-the-art methods.