Towards Unbounded Machine Unlearning
By Meghdad Kurmanji, Peter Triantafillou, Eleni Triantafillou. Neural Information Processing Systems, 2023
324 citations recorded by the source corpus.
Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion (RC) (caused by mislabelled data in trained models), as well as allowing users to exercise their `right to be forgotten' to protect User Privacy (UP). This paper is the first, to our knowledge, to study unlearning for different applications (RB, RC, UP), with the view that each has its own desiderata, definitions for `forgetting' and associated metrics for forget quality. For UP, we propose a novel adaptation of a strong Membership Inference Attack for unlearning. We also propose SCRUB, a novel unlearning algorithm, which is the only method that is consistently a top performer for forget quality across the different application-dependent metrics for RB, RC, and UP. At the same time, SCRUB is also consistently a top performer on metrics that measure model utility (i.e. accuracy on retained data and generalization), and is more efficient than previous work. The above are substantiated through a comprehensive empirical evaluation against previous state-of-the-art.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/570a341a8fd511cf0e05687110f053aaac646010
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
- Dan Hendrycks
- Mantas Mazeika
- Percy Liang
- Steven Basart
- Luke S. Zettlemoyer
- Quoc V. Le
- Dawn Song
- Jianfeng Gao
In Computer Vision and Pattern Recognition
- Mantas Mazeika
- Luc Van Gool
- Jimmy Ba
- Trevor Darrell
- Dan Hendrycks
- Dacheng Tao
- Xiaogang Wang
- Steven Basart
In Radiology, Nuclear Medicine and Imaging
Citations in the corpus
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (2024, methodology): “We benchmark RMU against three unlearning baselines: SCRUB (Kurmanji et al., 2023), SSD (Foster et al., 2024), and LLMU (Yao et al., 2023b), on ZEPHYR -7 B .”
- TOFU: A Task of Fictitious Unlearning for LLMs (2024, unknown): “In particular, these works consider a combination of forget quality and model utility, each using methods applicable in the classification context (Goel et al., 2022; Thudi et al., 2022; Kurmanji et al., 2023b).”