Machine Unlearning of Features and Labels

08/26/2021
by   Alexander Warnecke, et al.
0

Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose a method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/14/2022

Characterizing the Influence of Graph Elements

Influence function, a method from robust statistics, measures the change...
research
02/20/2023

Towards Unbounded Machine Unlearning

Deep machine unlearning is the problem of removing the influence of a co...
research
12/31/2020

Coded Machine Unlearning

Models trained in machine learning processes may store information about...
research
09/02/2022

An Introduction to Machine Unlearning

Removing the influence of a specified subset of training data from a mac...
research
10/18/2018

Removing the influence of a group variable in high-dimensional predictive modelling

Predictive modelling relies on the assumption that observations used for...
research
09/12/2017

Interpreting Shared Deep Learning Models via Explicable Boundary Trees

Despite outperforming the human in many tasks, deep neural network model...
research
05/30/2019

On the Accuracy of Influence Functions for Measuring Group Effects

Influence functions estimate the effect of removing particular training ...

Please sign up or login with your details

Forgot password? Click here to reset