AutoSMOTE uses Gumbel-Softmax to learn discrete oversampling rules per minority sample, reporting modest average-rank gains over SMOTE-family baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification
AutoSMOTE uses Gumbel-Softmax to learn discrete oversampling rules per minority sample, reporting modest average-rank gains over SMOTE-family baselines.