all AI news
Model Sparsification Can Simplify Machine Unlearning. (arXiv:2304.04934v3 [cs.LG] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Recent data regulations necessitate machine unlearning (MU): The removal of
the effect of specific examples from the model. While exact unlearning is
possible by conducting a model retraining with the remaining data from scratch,
its computational cost has led to the development of approximate but efficient
unlearning schemes. Beyond data-centric MU solutions, we advance MU through a
novel model-based viewpoint: sparsification via weight pruning. Our results in
both theory and practice indicate that model sparsity can boost the
multi-criteria unlearning …
advance approximation arxiv beyond boost computational cost data data-centric data regulations development examples gap machine novel performance practice pruning regulations solutions sparsity theory