A Systematic Literature Review of Machine Unlearning Techniques in Neural Networks
Open Access
Abstract
This review examines the field of machine unlearning in neural networks, an area driven by data privacy regulations such as the General Data Protection Regulation and the California Consumer Privacy Act. By analyzing 37 primary studies of machine unlearning applied to neural networks in both regression and classification tasks, this review thoroughly evaluates the foundational principles, key performance metrics, and methodologies used to assess these techniques. Special attention is given to recent advancements up to December 2023, including emerging approaches and frameworks. By categorizing and detailing these unlearning techniques, this work offers deeper insights into their evolution, effectiveness, efficiency, and broader applicability, thus providing a solid foundation for future research, development, and practical implementations in the realm of data privacy, model management, and compliance with evolving legal standards. Additionally, this review addresses the challenges of selectively removing data contributions at both the client and instance levels, highlighting the balance between computational costs and privacy guarantees.Keywords
This publication has 43 references indexed in Scilit:
- Fast Yet Effective Machine UnlearningIEEE Transactions on Neural Networks and Learning Systems, 2023
- Zero-Shot Machine UnlearningIEEE Transactions on Information Forensics and Security, 2023
- Efficient Two-stage Model Retraining for Machine Unlearning2022
- The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining2022
- FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models2021
- Coded Machine UnlearningIEEE Access, 2021
- Amnesiac Machine LearningProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Towards Making Systems Forget with Machine Unlearning2015
- The Algorithmic Foundations of Differential PrivacyFoundations and Trends® in Theoretical Computer Science, 2014
- Understanding the meaning of accuracy, trueness and precisionAccreditation and Quality Assurance, 2006