High-memorization training examples are forgotten fastest in class-incremental learning, and a cheap proxy based on learning iteration can guide buffer policies, favoring typical samples for small buffers and memorized ones for large buffers.
New insights on reducing abrupt representation change in online continual learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
What is the role of memorization in Continual Learning?
High-memorization training examples are forgotten fastest in class-incremental learning, and a cheap proxy based on learning iteration can guide buffer policies, favoring typical samples for small buffers and memorized ones for large buffers.