Abstract:
Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-trai...Show MoreMetadata
Abstract:
Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch. This paper develops a unified PAC-Bayesian framework for machine unlearning that recovers the two recent design principles - variational unlearning [1] and forgetting Lagrangian [2] as information risk minimization problems [3]. Accordingly, both criteria can be interpreted as PAC-Bayesian upper bounds on the test loss of the unlearned model that take the form of free energy metrics.
Published in: 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
Date of Conference: 25-28 October 2021
Date Added to IEEE Xplore: 15 November 2021
ISBN Information:
Print on Demand(PoD) ISSN: 1551-2541