Identifies output label space as a privacy side-channel in DP continual learning, formalizes DP for CL, and demonstrates two mitigation methods yielding higher accuracy than prior work.
Differentially Private Continual Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Catastrophic forgetting can be a significant problem for institutions that must delete historic data for privacy reasons. For example, hospitals might not be able to retain patient data permanently. But neural networks trained on recent data alone will tend to forget lessons learned on old data. We present a differentially private continual learning framework based on variational inference. We estimate the likelihood of past data given the current model using differentially private generative models of old datasets.
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Privacy Leakage via Output Label Space and Differentially Private Continual Learning
Identifies output label space as a privacy side-channel in DP continual learning, formalizes DP for CL, and demonstrates two mitigation methods yielding higher accuracy than prior work.