Machine Unlearning Method Based On Projection Residual
This addresses data privacy concerns for users and compliance with regulations by enabling more complete data forgetting in models, though it is incremental as it builds on existing unlearning methods.
The paper tackles the problem of machine unlearning, where models retain data effects even after removal, by proposing a projection residual method based on Newton iteration for linear regression and neural networks, achieving deletion thoroughness close to retraining as evaluated by feature injection testing.
Machine learning models (mainly neural networks) are used more and more in real life. Users feed their data to the model for training. But these processes are often one-way. Once trained, the model remembers the data. Even when data is removed from the dataset, the effects of these data persist in the model. With more and more laws and regulations around the world protecting data privacy, it becomes even more important to make models forget this data completely through machine unlearning. This paper adopts the projection residual method based on Newton iteration method. The main purpose is to implement machine unlearning tasks in the context of linear regression models and neural network models. This method mainly uses the iterative weighting method to completely forget the data and its corresponding influence, and its computational cost is linear in the feature dimension of the data. This method can improve the current machine learning method. At the same time, it is independent of the size of the training set. Results were evaluated by feature injection testing (FIT). Experiments show that this method is more thorough in deleting data, which is close to model retraining.