Machine Unlearning: Solutions and Challenges
arXiv:2308.07061 · doi:10.1109/TETCI.2024.3379240
Abstract
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific training data points' influence on trained models. This paper provides a comprehensive taxonomy and analysis of the solutions in machine unlearning. We categorize existing solutions into exact unlearning approaches that remove data influence thoroughly and approximate unlearning approaches that efficiently minimize data influence. By comprehensively reviewing solutions, we identify and discuss their strengths and limitations. Furthermore, we propose future directions to advance machine unlearning and establish it as an essential capability for trustworthy and adaptive machine learning models. This paper provides researchers with a roadmap of open problems, encouraging impactful contributions to address real-world needs for selective data removal.
References in corpus (13)
- Towards A Rigorous Science of Interpretable Machine Learning
- The information bottleneck method
- Differentially Private Empirical Risk Minimization
- New insights and perspectives on the natural gradient method
- Fast Yet Effective Machine Unlearning
- When Machine Unlearning Jeopardizes Privacy
- Zero-Shot Machine Unlearning
- Graph Unlearning
- A Survey of Machine Unlearning
- GIF: A General Graph Unlearning Strategy via Influence Function
- Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
- Verifiable and Provably Secure Machine Unlearning
- An Introduction to Machine Unlearning