2 papers
cs.LG2026
Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling
Pawel Pukowski, Venet Osmani
Class-bias, that is class-wise performance disparities, is typically attributed to data imbalance and addressed through frequency-based resampling. However, we demonstrate that sub…
cs.LG2024
Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance
Pawel Pukowski, Haiping Lu
In the AutoML domain, test accuracy is heralded as the quintessential metric for evaluating model efficacy, underpinning a wide array of applications from neural architecture searc…