LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the model -- up to an information theoretic bound -- mitigating its over-confidence that stems from data memorization. We evaluate LoTUS on the Transformer and ResNet18 models, against eight baseline methods, on five public datasets. Beyond established MU benchmarks, we evaluate unlearning on a large-scale dataset (ImageNet1k) which deters retraining, simulating real-world conditions. Moreover, we introduce the novel Retrain-Free Jensen-Shannon Divergence (RF-JSD) metric to enable evaluation under real-world conditions. Experimental results show that LoTUS outperforms state-of-the-art methods in terms of both efficiency and effectiveness. Code: https://github.com/cspartalis/LoTUS.