Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning

arXiv:2403.07611v1 Announce Type: new
Abstract: Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to adhere strictly to data protection regulations. However, existing unlearning techniques face practical constraints, often causing performance degradation, demanding brief fine-tuning post unlearning, and requiring significant storage. In response, this paper introduces a novel class of machine unlearning algorithms. First method is partial …

abstract arxiv attention capability cs.ai cs.lg data data protection face however knowledge layer machine machine learning machine learning model protection regulations samples through training training data type unlearning wise