Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.06360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913563105296384 |
|---|---|
| author | Shaik, Thanveer Tao, Xiaohui Xie, Haoran Li, Lin Zhu, Xiaofeng Li, Qing |
| author_facet | Shaik, Thanveer Tao, Xiaohui Xie, Haoran Li, Lin Zhu, Xiaofeng Li, Qing |
| contents | Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models. While training models have become more efficient and accurate, the importance of unlearning previously learned information has become increasingly significant in fields such as privacy, security, and fairness. This paper presents a comprehensive survey of MU, covering current state-of-the-art techniques and approaches, including data deletion, perturbation, and model updates. In addition, commonly used metrics and datasets are also presented. The paper also highlights the challenges that need to be addressed, including attack sophistication, standardization, transferability, interpretability, training data, and resource constraints. The contributions of this paper include discussions about the potential benefits of MU and its future directions. Additionally, the paper emphasizes the need for researchers and practitioners to continue exploring and refining unlearning techniques to ensure that ML models can adapt to changing circumstances while maintaining user trust. The importance of unlearning is further highlighted in making Artificial Intelligence (AI) more trustworthy and transparent, especially with the increasing importance of AI in various domains that involve large amounts of personal user data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_06360 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy Shaik, Thanveer Tao, Xiaohui Xie, Haoran Li, Lin Zhu, Xiaofeng Li, Qing Machine Learning Artificial Intelligence Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models. While training models have become more efficient and accurate, the importance of unlearning previously learned information has become increasingly significant in fields such as privacy, security, and fairness. This paper presents a comprehensive survey of MU, covering current state-of-the-art techniques and approaches, including data deletion, perturbation, and model updates. In addition, commonly used metrics and datasets are also presented. The paper also highlights the challenges that need to be addressed, including attack sophistication, standardization, transferability, interpretability, training data, and resource constraints. The contributions of this paper include discussions about the potential benefits of MU and its future directions. Additionally, the paper emphasizes the need for researchers and practitioners to continue exploring and refining unlearning techniques to ensure that ML models can adapt to changing circumstances while maintaining user trust. The importance of unlearning is further highlighted in making Artificial Intelligence (AI) more trustworthy and transparent, especially with the increasing importance of AI in various domains that involve large amounts of personal user data. |
| title | Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2305.06360 |