A new loss and memory update improve Macro-AUC in imbalanced multi-label continual learning, backed by theoretical bounds of questionable validity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning
A new loss and memory update improve Macro-AUC in imbalanced multi-label continual learning, backed by theoretical bounds of questionable validity.