VAE-Inf trains a VAE on majority data to build a reference distribution, then uses limited minority samples and a projection score to produce classifiers with guaranteed control of false-positive rates in imbalanced settings.
Over-sampling algorithm based on vae in imbalanced classification
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
-
VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification
VAE-Inf trains a VAE on majority data to build a reference distribution, then uses limited minority samples and a projection score to produce classifiers with guaranteed control of false-positive rates in imbalanced settings.