.png){kind=icon}
.png){kind=icon}
Return
Rare but critical: Copula-calibrated augmentation for imbalanced tabular regression
.png){kind=icon}
PRE
AI
N
DOI：10.1016/j.neucom.2026.134638.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Rare target cases are predicted poorly by standard tabular models. • CopulaCalib augments only the scarce target regions with synthetic rows. • A region-specific copula preserves feature correlations during generation. • Synthetic rows stay plausible, unlike interpolation or moment matching. • It runs in under a second without training a deep generative model.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers