# Addressing Multilabel Imbalance with an Efficiency-Focused Approach Using Diffusion Model-Generated Synthetic Samples

arXiv: https://arxiv.org/abs/2501.10822 · HTML: https://mlsanity.com/paper/2501.10822/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 1 of its 55 references that are in the map.
- First posted on arXiv 18 Jan 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 1 of 1)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)

## Abstract (arXiv)

Predictive models trained on imbalanced data tend to produce biased results. This problem is exacerbated when there is not just one output label, but a set of them. This is the case for multilabel learning (MLL) algorithms used to classify patterns, rank labels, or learn the distribution of outputs. Many solutions have been proposed in the literature. The one that can be applied universally, independent of the algorithm used to build the model, is data resampling. The generation of new instances associated with minority labels, so that empty areas of the feature space are filled, helps to improve the obtained models. The quality of these new instances depends on the algorithm used to generate them. In this paper, a diffusion model tailored to produce new instances for MLL data, called MLDM (textitMultiLabel Diffusion Model), is proposed. Diffusion models have been mainly used to generate artificial images and videos. Our proposed MLDM is based on this type of models. The experiments conducted compare MLDM with several other MLL resampling algorithms. The results show that MLDM is competitive while it improves efficiency.