Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model performance is still challenging. In this paper, we propose a contrastive unlearning framework, leveraging the concept of representation learning for more effective unlearning. It removes the influence of unlearning samples by contrasting their embeddings against the remaining samples so that they are pushed away from their original classes and pulled toward other classes. By directly optimizing the representation space, it effectively removes the influence of unlearning samples while maintaining the representations learned from the remaining samples. Experiments on a variety of datasets and models on both class unlearning and sample unlearning showed that contrastive unlearning achieves the best unlearning effects and efficiency with the lowest performance loss compared with the state-of-the-art algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine UnlearningRepresentation LearningSimilar Papers 제목 키워드 기반
Alignment Calibration: Machine Unlearning for Contrastive Learning under Auditing
Machine unlearning provides viable solutions to revoke the effect of certain training data on pre-trained model parameters. Existing approaches provide unlearning recipes for classification and generative models. However…
Contrastive LearningMachine UnlearningMachine Unlearning in Contrastive Learning
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 re…
Contrastive LearningMachine UnlearningSelf-Supervised LearningWSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification
Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based stra…
Contrastive LearningImage ClassificationUCD: Unlearning in LLMs via Contrastive Decoding
Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm tha…
Machine UnlearningMachine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Machine unlearning methods have become increasingly important for selective concept removal in large pre-trained models. While recent work has explored unlearning in Euclidean contrastive vision-language models, the effe…
Contrastive LearningMachine Unlearning