A unified PAC-Bayesian framework for machine unlearning via information risk minimization
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 (Nguyen et.al., 2020) and forgetting Lagrangian (Golatkar et.al., 2020) - as information risk minimization problems (Zhang,2006). 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine UnlearningSimilar Papers 제목 키워드 기반
A Unified Framework for Continual Learning and Unlearning
Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. Continual learning focuses on adapting to new knowledge while preserving past information, whereas unl…
Continual LearningKnowledge DistillationMachine UnlearningMachine Unlearning via Information Theoretic Regularization
How can we effectively remove or "unlearn" undesirable information, such as specific features or individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees? We introduc…
Machine UnlearningMUBox: A Critical Evaluation Framework of Deep Machine Unlearning
Recent legal frameworks have mandated the right to be forgotten, obligating the removal of specific data upon user requests. Machine Unlearning has emerged as a promising solution by selectively removing learned informat…
Machine UnlearningGraph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models
The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory compliance, and adaptive system design. We introduce Graph-Propagated…
Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective
In order to adhere to regulatory standards governing individual data privacy and safety, machine learning models must systematically eliminate information derived from specific subsets of a user's training data that can …
Machine Unlearning