# Generative Oversampling for Imbalanced Data via Majority-Guided VAE

arXiv: https://arxiv.org/abs/2302.10910 · HTML: https://mlsanity.com/paper/2302.10910/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 56 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data](https://mlsanity.com/paper/1508.03422/) (2015)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [M2m: Imbalanced Classification via Major-to-minor Translation](https://mlsanity.com/paper/2004.00431/) (2020)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification](https://mlsanity.com/paper/2112.00412/) (2021)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Learning Fast Sample Re-weighting Without Reward Data](https://mlsanity.com/paper/2109.03216/) (2021)
- [Imbalanced Deep Learning by Minority Class Incremental Rectification](https://mlsanity.com/paper/1804.10851/) (2018)
- [G2D: Generate to Detect Anomaly](https://mlsanity.com/paper/2006.11629/) (2020)
- [Label-Aware Distribution Calibration for Long-tailed Classification](https://mlsanity.com/paper/2111.04901/) (2021)
- [Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning](https://mlsanity.com/paper/1511.09337/) (2015)
- [ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE](https://mlsanity.com/paper/2107.09286/) (2021)

## Built on by (most cited first, 10 of 10)

- [On the Usefulness of Synthetic Tabular Data Generation](https://mlsanity.com/paper/2306.15636/) (2023)
- [Restoring balance: principled under/oversampling of data for optimal classification](https://mlsanity.com/paper/2405.09535/) (2024)
- [Data Augmentation with Variational Autoencoder for Imbalanced Dataset](https://mlsanity.com/paper/2412.07039/) (2024)
- [Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance](https://mlsanity.com/paper/2605.06289/) (2026)
- [C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior](https://mlsanity.com/paper/2309.13303/) (2023)
- [Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model](https://mlsanity.com/paper/2507.09052/) (2025)
- [Disentangled Deep Smoothed Bootstrap for Fair Imbalanced Regression](https://mlsanity.com/paper/2508.13829/) (2025)
- [Learning Majority-to-Minority Transformations with MMD and Triplet Loss for Imbalanced Classification](https://mlsanity.com/paper/2509.11511/) (2025)
- [Uncertainty-Aware Generative Oversampling Using an Entropy-Guided Conditional Variational Autoencoder](https://mlsanity.com/paper/2509.25334/) (2025)
- [Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning](https://mlsanity.com/paper/2603.13927/) (2026)

## Abstract (arXiv)

Learning with imbalanced data is a challenging problem in deep learning. Over-sampling is a widely used technique to re-balance the sampling distribution of training data. However, most existing over-sampling methods only use intra-class information of minority classes to augment the data but ignore the inter-class relationships with the majority ones, which is prone to overfitting, especially when the imbalance ratio is large. To address this issue, we propose a novel over-sampling model, called Majority-Guided VAE~(MGVAE), which generates new minority samples under the guidance of a majority-based prior. In this way, the newly generated minority samples can inherit the diversity and richness of the majority ones, thus mitigating overfitting in downstream tasks. Furthermore, to prevent model collapse under limited data, we first pre-train MGVAE on sufficient majority samples and then fine-tune based on minority samples with Elastic Weight Consolidation(EWC) regularization. Experimental results on benchmark image datasets and real-world tabular data show that MGVAE achieves competitive improvements over other over-sampling methods in downstream classification tasks, demonstrating the effectiveness of our method.