Representation discrepancy, a new metric with theoretical bounds, shows continual learning forgets features faster in deeper layers and slower in wider networks.
Memory bounds for continual learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
Representation discrepancy, a new metric with theoretical bounds, shows continual learning forgets features faster in deeper layers and slower in wider networks.