A Survey of Machine Unlearning

By Thanh Tam Nguyen, T. Huynh, Phi-Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, Quoc Viet Hung Nguyen. ACM Transactions on Intelligent Systems and Technology, 2022

439 citations recorded by the source corpus.

Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in AI, and especially machine learning, its existence can be a threat to user privacy, and it can weaken the bonds of trust between humans and AI. Recent regulations now require that, on request, private information about a user must be removed both from computer systems and from machine learning models—this legislation is more colloquially called “the right to be forgotten.” While removing data from back-end databases should be straightforward, it is not sufficient in the AI context as machine learning models often “remember” the old data. Contemporary adversarial attacks on trained models have proven that we can learn whether an instance or an attribute belonged to the training data. This phenomenon calls for a new paradigm, namely machine unlearning, to make machine learning models forget about particular data. It turns out that recent works on machine unlearning have not been able to completely solve the problem due to the lack of common frameworks and resources. Therefore, this article aspires to present a comprehensive examination of machine unlearning’s concepts, designs, methods, and applications. Specifically, as a category collection of cutting-edge studies, the intention behind this article is to serve as a comprehensive resource for researchers and practitioners seeking an introduction to machine unlearning and its formulations, design criteria, removal requests, algorithms, and applications. In addition, we aim to highlight the key findings, current trends, and new research areas that have not yet featured the use of machine unlearning but could benefit greatly from it. We hope that this survey serves as a valuable resource for machine learning researchers and those seeking to innovate privacy technologies. Our resources are publicly available at https://github.com/tamlhp/awesome-machine-unlearning.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/59027b574cd02905cbdcb1fd8feefb878cc49c8d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Mechanistic Interpretability for AI Safety - A Review (2024, background): “This focus on cherry-picked results from toy models is a form of streetlight interpretability (Casper, 2023), examining AI systems under only ideal conditions of maximal interpretability.”
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning (2024, background): “Machine unlearning (Cao & Yang, 2015; Bourtoule et al., 2021) aims to delete the influence of specific training samples from machine-learning models while preserving other knowledge and capabilities (Liu et al., 2024a; Zhang et al., 2023; Nguyen et al., 2022; Xu et al., 2023; Si et al., 2023).”
Rethinking machine unlearning for large language models (2024, neutral): “The study of MU can be traced back to non-LLMs in response to data protection regulations such as ‘the right to be forgotten’ Cao & Yang (2015); Hoofnagle et al. (2019); Bourtoule et al. (2021); Nguyen et al. (2022).”
Cognitive Architectures for Language Agents (2023, background): “…for specific reasoning sub-tasks (Zelikman et al., 2022; Huang et al., 2022a; Ahn et al., 2022), deleting unneeded memory items for “unlearning” (Nguyen et al., 2022c), and studying the interaction effects between multiple forms of learning (Tuyls et al., 2022; Park et al., 2023; Xie et al.,…”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “While the interest in the machine unlearning paradigm [280] has been on the rise [281], it is unclear how to efficiently ensure that data owned by a particular user is unlearned by a given large-scale generative model, so that it can be ensured that no instance like that of the user claiming their…”