UnAct: Gradient-Free Unlearning via Targeted Activation Intervention

Researchers introduced UnAct, a gradient-free machine unlearning method that removes the influence of designated training data by intervening on targeted activations rather than retraining or backpropagating. UnAct is positioned against retrain-free baselines Selective Synaptic Dampening (SSD) and its label-free variant LFSSD, which the authors note still require backpropagation and parameter updates.

Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening SSD and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter im