Learning to Forget using Hypernetworks
Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations. The objective is to unlearn the effect of undesired data from a trained model while maintaining performance on the remaining data. This paper introduces HyperForget, a novel machine unlearning framework that leverages hypernetworks - neural networks that generate parameters for other networks - to dynamically sample models that lack knowledge of targeted data while preserving essential capabilities. Leveraging diffusion models, we implement two Diffusion HyperForget Networks and used them to sample unlearned models in Proof-of-Concept experiments. The unlearned models obtained zero accuracy on the forget set, while preserving good accuracy on the retain sets, highlighting the potential of HyperForget for dynamic targeted data removal and a promising direction for developing adaptive machine unlearning algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Data PoisoningMachine UnlearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Partial Hypernetworks for Continual Learning
Hypernetworks mitigate forgetting in continual learning (CL) by generating task-dependent weights and penalizing weight changes at a meta-model level. Unfortunately, generating all weights is not only computationally exp…
Continual LearningPrototype Augmented Hypernetworks for Continual Learning
Continual learning (CL) aims to learn a sequence of tasks without forgetting prior knowledge, but gradient updates for a new task often overwrite the weights learned earlier, causing catastrophic forgetting (CF). We prop…
Continual LearningContinual learning with hypernetworks
Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., ne…
Continual LearningTransfer LearningSHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Traditional deep neural networks suffer from several limitations, including catastrophic forgetting. When models are adapted to new datasets, they tend to quickly forget previously learned knowledge. Another significant …
Continual LearningContinual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning
Buildings with Heating, Ventilation, and Air Conditioning (HVAC) systems play a crucial role in ensuring indoor comfort and efficiency. While traditionally governed by physics-based models, the emergence of big data has …
Continual LearningDeep Reinforcement LearningModel-based Reinforcement Learningreinforcement-learning+3