Machine Unlearning in Contrastive Learning

TL;DR

This paper introduces a gradient constraint-based method for machine unlearning in contrastive learning models, which is efficient, requires few training epochs, and is versatile across different learning paradigms.

Contribution

It presents a novel approach for machine unlearning in contrastive learning, addressing a gap in existing research primarily focused on supervised models.

Findings

Effective unlearning with minimal epochs

Applicable to both contrastive and supervised models

Maintains model accuracy after unlearning

Abstract

Machine unlearning is a complex process that necessitates the model to diminish the influence of the training data while keeping the loss of accuracy to a minimum. Despite the numerous studies on machine unlearning in recent years, the majority of them have primarily focused on supervised learning models, leaving research on contrastive learning models relatively underexplored. With the conviction that self-supervised learning harbors a promising potential, surpassing or rivaling that of supervised learning, we set out to investigate methods for machine unlearning centered around contrastive learning models. In this study, we introduce a novel gradient constraint-based approach for training the model to effectively achieve machine unlearning. Our method only necessitates a minimal number of training epochs and the identification of the data slated for unlearning. Remarkably, our approach demonstrates proficient performance not only on contrastive learning models but also on supervised learning models, showcasing its versatility and adaptability in various learning paradigms.