# Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification

arXiv: https://arxiv.org/abs/2502.06878 · HTML: https://mlsanity.com/paper/2502.06878/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 42 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [Deep Over-sampling Framework for Classifying Imbalanced Data](https://mlsanity.com/paper/1704.07515/) (2017)
- [Oversampling for Imbalanced Learning Based on K-Means and SMOTE](https://mlsanity.com/paper/1711.00837/) (2017)
- [Sparse Kernel PCA for Outlier Detection](https://mlsanity.com/paper/1809.02497/) (2018)

## Built on by (most cited first, 3 of 3)

- [AxelSMOTE: An Agent-Based Oversampling Algorithm for Imbalanced Classification](https://mlsanity.com/paper/2509.06875/) (2025)
- [Orthogonal Activation with Implicit Group-Aware Bias Learning for Class Imbalance](https://mlsanity.com/paper/2512.20006/) (2025)
- [Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure](https://mlsanity.com/paper/2607.11994/) (2026)

## Abstract (arXiv)

Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue, traditional sampling techniques are often decoupled from the training phase of the predictive model, resulting in suboptimal representations. To address this, we propose a novel learning framework that can generate synthetic data instances in a data-driven manner. The proposed framework formulates the oversampling process as a composition of discrete decision criteria, thereby enhancing the representation power of the model's learning process. Extensive experiments on the imbalanced classification task demonstrate the superiority of our framework over state-of-the-art algorithms.