A framework using sparse autoencoders decomposes concept-level forgetting in supervised continual learning into apparent deletion, recoverability, and decodability, showing substantial recoverability under linearity and degrading decodability with added tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
A framework using sparse autoencoders decomposes concept-level forgetting in supervised continual learning into apparent deletion, recoverability, and decodability, showing substantial recoverability under linearity and degrading decodability with added tasks.