Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911760820207616 |
|---|---|
| author | Lee, Hong kyu Zhang, Qiuchen Yang, Carl Lou, Jian Xiong, Li |
| author_facet | Lee, Hong kyu Zhang, Qiuchen Yang, Carl Lou, Jian Xiong, Li |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10458 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive Unlearning: A Contrastive Approach to Machine Unlearning Lee, Hong kyu Zhang, Qiuchen Yang, Carl Lou, Jian Xiong, Li Machine Learning Cryptography and Security 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. |
| title | Contrastive Unlearning: A Contrastive Approach to Machine Unlearning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2401.10458 |