Conference proceeding
Mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation
Algorithms and Architectures for Parallel Processing: 24th International Conference, ICA3PP 2024, Macau, China, October 29–31, 2024, Proceedings, Part IV, pp.300-314
24th International Conference, ICA3PP 2024, 24th (Macau, China, 29/10/2024–31/10/2024)
02/2025
Metrics
1 Record Views
Abstract
In machine learning, data privacy and security has become an increasingly growing concern. The introduction of machine unlearning offers the ability to address this issue through the removal of personal and sensitive data from trained models to comply with laws, regulations, and user privacy requirements. However, despite the significant benefits of this technique, performing unlearning operations is only sometimes smooth in practice. When we attempt to remove specific data, the model may over-adjust, resulting in its performance on unlearned data. This phenomenon not only reduces the accuracy of the model on known data but also affects its ability to generalize new data, thus weakening the model’s overall performance. Therefore, in this paper, we analyze the phenomenon of over-unlearning; firstly, we explore how to mitigate the effects of over-unlearning by generating synthetic data to fill in the forgotten parts, using data synthesis-based techniques. Secondly, we combine the data synthesis-based compensation strategy with model fine-tuning to further improve the model’s adaptability and generalization capability by further training the model to accommodate synthetic data. Through comprehensive experimentation, we verify the effectiveness of the proposed data synthesis-based compensation strategy. The experimental results show that the data synthesis-based compensation strategy can effectively mitigate the effects of the over-unlearning phenomenon, as well as maintaining the stability and accuracy of the model after removing specific data.
Details
- Title
- Mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation
- Creators
- Baohai Wang - National Supercomputer Center (China)Youyang Qu - CSIROLongxiang Gao - National Supercomputer Center (China)Conggai Li - CSIROLin Li - Royal Melbourne Institute of Technology (Australia, Melbourne)David J. Smith - CSIRO
- Contributors
- Tianqing Zhu (Editor) - City University of MacauAniello Castiglione (Editor) - University of SalernoJin Li (Editor) - Guangzhou University
- Publication Details
- Algorithms and Architectures for Parallel Processing: 24th International Conference, ICA3PP 2024, Macau, China, October 29–31, 2024, Proceedings, Part IV, pp.300-314
- Conference
- 24th International Conference, ICA3PP 2024, 24th (Macau, China, 29/10/2024–31/10/2024)
- Publisher
- Springer; Singapore
- Number of pages
- 15
- Identifiers
- 991013285342102368
- Copyright
- © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
- Academic Unit
- Faculty of Science and Engineering
- Language
- English
- Resource Type
- Conference proceeding