TY - JOUR
T1 - Simplifying Neural Network Training Under Class Imbalance
AU - Shwartz-Ziv, Ravid
AU - Goldblum, Micah
AU - Li, Yucen Lily
AU - Bruss, C. Bayan
AU - Wilson, Andrew Gordon
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models.The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures.Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods.We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.
AB - Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models.The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures.Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods.We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.
UR - http://www.scopus.com/inward/record.url?scp=85185582961&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85185582961&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85185582961
SN - 1049-5258
VL - 36
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
Y2 - 10 December 2023 through 16 December 2023
ER -