Machine Unlearning of Features and Labels
By Alexander Warnecke, Lukas Pirch, Christian Wressnegger, Konrad Rieck. Network and Distributed System Security Symposium, 2021
322 citations recorded by the source corpus.
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose the first method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/128a14c3048f328c8e4ce9c274b0bf467946a57f
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
- Large Language Model Unlearning (2023, background): “…for classification models, including data-reversed training [Tarun et al., 2023, Liu et al., 2022, Chundawat et al., 2023], optimization-based unlearning [Guo et al., 2019, Neel et al., 2021] and influence function based approaches [Jia et al., 2023, Warnecke et al., 2021, Izzo et al., 2021].”
- SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation (2023, methodology): “4, FT (Warnecke et al., 2021), RL (Golatkar et al., 2020), GA (Thudi et al., 2022a), IU (Izzo et al., 2021; Jia et al., 2023), ℓ 1 -sparse (Jia et al., 2023), as well as 4 new baselines , including 2 boundary unlearning methods (Chen et al., 2023), boundary shrink ( BS ) and boundary expanding ( BE…”
- Rethinking machine unlearning for large language models (2024, unknown): “…function (Koh & Liang, 2017; Bae et al., 2022) is a standard approach to assess the effect of data removal on model performance (Izzo et al., 2021; Warnecke et al., 2021), it is not commonly employed in the context of LLM unlearning for two main reasons: the computational complexity involved in…”