# ART: Adaptive Resampling-based Training for Imbalanced Classification

arXiv: https://arxiv.org/abs/2509.00955 · HTML: https://mlsanity.com/paper/2509.00955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Class-Difficulty Based Methods for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.14499/) (2022)
- [AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning](https://mlsanity.com/paper/1911.12110/) (2019)

## Abstract (arXiv)

Traditional resampling methods for handling class imbalance typically uses fixed distributions, undersampling the majority or oversampling the minority. These static strategies ignore changes in class-wise learning difficulty, which can limit the overall performance of the model. This paper proposes an Adaptive Resampling-based Training (ART) method that periodically updates the distribution of the training data based on the class-wise performance of the model. Specifically, ART uses class-wise macro F1 scores, computed at fixed intervals, to determine the degree of resampling to be performed. Unlike instance-level difficulty modeling, which is noisy and outlier-sensitive, ART adapts at the class level. This allows the model to incrementally shift its attention towards underperforming classes in a way that better aligns with the optimization objective. Results on diverse benchmarks, including Pima Indians Diabetes and Yeast dataset demonstrate that ART consistently outperforms both resampling-based and algorithm-level methods, including Synthetic Minority Oversampling Technique (SMOTE), NearMiss Undersampling, and Cost-sensitive Learning on binary as well as multi-class classification tasks with varying degrees of imbalance. In most settings, these improvements are statistically significant. On tabular datasets, gains are significant under paired t-tests and Wilcoxon tests (p < 0.05), while results on text and image tasks remain favorable. Compared to training on the original imbalanced data, ART improves macro F1 by an average of 2.64 percentage points across all tested tabular datasets. Unlike existing methods, whose performance varies by task, ART consistently delivers the strongest macro F1, making it a reliable choice for imbalanced classification.