Share your thoughts, 1 month free Claude Pro on usSee more
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
Knowledge RetentionMMLU (full)
MMLU Accuracy43.6
60
Machine UnlearningTOFU Forget 1%
Aggregation Score50
54
Machine UnlearningTOFU forget05 1.0
Model Utility (MU)62
53
Machine UnlearningTOFU 1.0 (forget01)
Average Score57
53
ClassificationMLLMU-Bench Forget Set
Accuracy60.83
51
Machine UnlearningTOFU
Forget Quality (FQ)0.0268
43
Multimodal UnderstandingMMBench
Classification Score89.65
42
Visual Question Answering (VQA)MLLMU-Bench 5% (forget)
Accuracy (Classification)49.17
42
GenerationMLLMU-Bench Forget Set
Rouge Score50.2
37
Multimodal Machine Unlearning EvaluationMLLMU-Bench Forget Set
Classification Accuracy40.38
36
Showing 10 of 114 rows
...

Other info

Follow for update