Search Results for author:
Found 3 papers, 0 papers with code
Federated Unlearning for Human Activity Recognition
In response, we propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data.
Machine unlearning via GAN
Machine learning models, especially deep models, may unintentionally remember information about their training data.
Lightweight machine unlearning in neural network
Our method only needs to make a small perturbation of the weight of the target model and make it iterate in the direction of the model trained with the remaining data subset until the contribution of the unlearning data to the model is completely eliminated.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
