Machine Unlearning: A Comprehensive Survey

TL;DR

This comprehensive survey reviews machine unlearning techniques, categorizing methods, discussing verification, privacy issues, and future challenges in the context of privacy legislation.

Contribution

It systematically classifies and analyzes various machine unlearning methods, including centralized, distributed, and security aspects, highlighting open problems and future directions.

Findings

Classifies unlearning into exact and approximate methods.

Introduces federated and graph unlearning as emerging directions.

Discusses verification and privacy/security issues in unlearning.

Abstract

As the right to be forgotten has been legislated worldwide, many studies attempt to design unlearning mechanisms to protect users' privacy when they want to leave machine learning service platforms. Specifically, machine unlearning is to make a trained model to remove the contribution of an erased subset of the training dataset. This survey aims to systematically classify a wide range of machine unlearning and discuss their differences, connections and open problems. We categorize current unlearning methods into four scenarios: centralized unlearning, distributed and irregular data unlearning, unlearning verification, and privacy and security issues in unlearning. Since centralized unlearning is the primary domain, we use two parts to introduce: firstly, we classify centralized unlearning into exact unlearning and approximate unlearning; secondly, we offer a detailed introduction to the techniques of these methods. Besides the centralized unlearning, we notice some studies about distributed and irregular data unlearning and introduce federated unlearning and graph unlearning as the two representative directions. After introducing unlearning methods, we review studies about unlearning verification. Moreover, we consider the privacy and security issues essential in machine unlearning and organize the latest related literature. Finally, we discuss the challenges of various unlearning scenarios and address the potential research directions.