Lightweight machine unlearning in neural network

Abstract

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely manner, stipulating that individuals have the right to withdraw their consent from personal information processing activities based on their consent. To solve this problem, machine unlearning is proposed, which allows the model to erase all memory of private information. Previous studies, including retraining and incremental learning to update models, often take up extra storage space or are difficult to apply to neural networks. 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. In this paper, experiments on five datasets prove the effectiveness of our method for machine unlearning, and our method is 15 times faster than retraining.

On the Effectiveness of Unlearning in Session-Based Recommendation

“…[18] utilized a probabilistic model to approximate the unlearning process. [7,25] proposed to perturb the gradients or model weights through the inverse Hessian matrix, which may incur additional computational overheads.…”

Fast and Accurate SNN Model Strengthening for Industrial Applications

“…A simple and naive solution is to delete the malicious data samples from the training data and retrain the model, which is usually quite time-consuming due to the huge computational load. There are several solutions to address this problem in an efficient way [14][15][16][17]. For example, Cao [18] divided the training data into several groups, removed the group with malicious data samples, and updated the whole model accordingly.…”