Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Continual Learning and Private Unlearning

About

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.

Bo Liu, Qiang Liu, Peter Stone• 2022

Related benchmarks

TaskDatasetResultRank
Machine UnlearningTOFU
Forget Quality (FQ)0.0268
43
Visual Question AnsweringCLEAR 1.0 (Retain)
Accuracy66
32
LLM UnlearningTOFU 5% (forget set)
FQ-13.232
25
Multimodal Machine UnlearningMLLMU-Bench LLaVA-1.5-7B (test 2)
Forget Rate60.4
24
Machine UnlearningUnlearning Evaluation Dataset Forget, Retain, and Non-member sets
SQS75.1
24
Multimodal Machine UnlearningMLLMU-Bench LLaVA-1.5-7B (test 1)
Forget Rate60.6
24
Machine Unlearning5% (forget set)
GF18.287
24
ClassificationMLLMU-Bench Forget Set
Accuracy0.436
21
Machine UnlearningTOFU 10% forget set 1.0
FQ-26.8
18
Machine UnlearningTOFU 1% (forget set)
FQ-1.845
18
Showing 10 of 39 rows

Other info

Follow for update