MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
This addresses the need for effective data revocation in contrastive learning, a critical domain in machine learning, though it is incremental as it adapts existing unlearning methods to a new model category.
The paper tackles the problem of machine unlearning for contrastive learning models, which had been overlooked, by introducing the MUC framework and a novel method called Alignment Calibration that achieves state-of-the-art performance, approximating exact unlearning (retraining) on models like SimCLR, MoCo, and CLIP.
Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for classification and generative models, they overlook an important category of machine learning models: contrastive learning (CL) methods. This paper addresses this gap by introducing the Machine Unlearning for Contrastive Learning (MUC) framework and adapting existing methods. We identify limitations in current approaches, noting that several methods perform inadequately as unlearners and that existing evaluation tools insufficiently validate unlearning effects in contrastive learning. To address these issues, we propose Alignment Calibration (AC), a novel method that explicitly considers contrastive learning properties and optimizes towards new auditing metrics for easy verification of unlearning. Through empirical comparisons with baseline methods on SimCLR, MoCo, and CLIP, we demonstrate that AC: (1) achieves state-of-the-art performance, approximating exact unlearning (retraining); (2) enables data owners to clearly visualize unlearning effects through black-box evaluation. The code is available at https://github.com/EhanW/Alignment-Calibration.