Continual Learning and Private Unlearning

By Bo Liu, Qian Liu, Peter Stone. 2022

152 citations recorded by the source corpus.

As intelligent agents become autonomous over longer periods of time, they may eventually become lifelong counterparts to specific people. If so, it may be common for a user to want the agent to master a task temporarily but later on to forget the task due to privacy concerns. However enabling an agent to \emph{forget privately} what the user specified without degrading the rest of the learned knowledge is a challenging problem. With the aim of addressing this challenge, this paper formalizes this continual learning and private unlearning (CLPU) problem. The paper further introduces a straightforward but exactly private solution, CLPU-DER++, as the first step towards solving the CLPU problem, along with a set of carefully designed benchmark problems to evaluate the effectiveness of the proposed solution. The code is available at https://github.com/Cranial-XIX/Continual-Learning-Private-Unlearning.

How researchers see this paper

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

Citations in the corpus

The Ideal Continual Learner: An Agent That Never Forgets (2023, positive): “The point here is that, this classic line of research furnished the very rudimentary idea of what is recently known as selective forgetting or active forgetting in the deep continual learning context (Aljundi et al., 2018; Wang et al., 2021a; Shibata et al., 2021; Liu et al., 2022).”
TOFU: A Task of Fictitious Unlearning for LLMs (2024, unknown): “Consider the case of unlearning the 5% forget set with Gradient Difference on Llama-2-7B, Figure 17.”
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning (2023, unknown): “But as the lifelong learner mainly learns from humans, studying how to preserve user privacy within LLDM [36] is crucial in the long run.”