Active forgetting via influence estimation for neural networks

Abstract

The rapidly exploding of user data, especially applications of neural networks, involves analyzing data collected from individuals, which brings convenience to life. Meanwhile, privacy leakage in the applications 1% and 3% accuracy drop with more than 80% forgetting rate on average for logistic regression models and convolutional neural networks. The accuracy drop is reduced by 2%-3% compared to most state-of-the-art methods.